LING073 - User contributions [en]

Wolof/Final project

2023-05-09T15:03:52Z

Rorlija1: /* Evaluation */

==Keyboard suite==

==Code==

==Evaluation==

[[Category:Sp23_FinalProjects]],[[Category:Wolof]]

Wolof/Final project

2023-05-09T15:02:20Z

Rorlija1: creating

==Keyboard suite==

==Code==

==Evaluation==

Sardinian and English

2023-05-05T19:42:33Z

Rorlija1: /* Final evaluation */

=Resources for Machine Translation from Sardinian to English=

==Developed Resources==
*[https://github.swarthmore.edu/Ling073-sp23/ling073-srd-eng-corpus Parallel corpus git repo].
*:Lines 1-8 from [http://maxia-mail.doomby.com/ this website].
*[https://github.swarthmore.edu/Ling073-sp23/ling073-srd-eng Git repo for language pair]
*[https://github.swarthmore.edu/Ling073-sp23/ling073-srd Git repo for Sardinian]
*[https://github.com/apertium/apertium-eng Forked git repo for English]
*[https://wikis.swarthmore.edu/ling073/Sardinian_and_English/Lexical_selection#srd_.E2.86.92_eng Lexical selection wiki]
*[https://wikis.swarthmore.edu/ling073/Sardinian_and_English/Contrastive_Grammar#Differences_in_parse_and_corresponding_examples Contrastive grammar wiki]
*[https://wikis.swarthmore.edu/ling073/Sardinian_and_English/Structural_transfer Structural transfer wiki]

==srd → eng evaluation==
*coverage of monolingual Sardinian transducer on srd.sentences.txt:
Number of tokenised words in the corpus: 262
Coverage: 94.66%
*coverage of bilingual transducer on srd.sentences
Number of tokenised words in the corpus: 266
Coverage: 85.71%

==Additions for polished RBMT system==
*Over 100 new stems to bilingual dictionary
*:(now we have 172 total entries in the .dix file)
*4 sets of lexical selection rules
*:(now we have rules that solve 5 problems in total)
*3 items from contrastive grammar implemented in transfer rules
*:(now we have rules that implement 4 total items)

==Final evaluation==
* For the monolingual transducer:
** Precision and recall against srd.sentences.txt (1314 char):
Totals: 145 forms, 417 tp, 0 fp, 0 tn, 11 fn
Precision: 100.00000%
Recall: 97.42991%
** Coverage over the <code>large</code> corpus:
*** 90.4% with monolingual transducer: (mostly simple words that could easily be added)

TOP UNKNOWN WORDS:
2336 ^po/*po$
1275 ^che/*che$
448 ^i/*i$
387 ^norte/*norte$
377 ^The/*The$
353 ^of/*of$
297 ^poi/*poi$
269 ^del/*del$
241 ^the/*the$
235 ^da/*da$
215 ^ch/*ch$
211 ^Il/*Il$
205 ^chentza/*chentza$
200 ^br/*br$
199 ^Arbaree/*Arbaree$
197 ^della/*della$
192 ^stètiu/*stètiu$
165 ^ddoi/*ddoi$
154 ^B/*B$
145 ^Norte/*Norte$
coverage: 1648134 / 1822907 (~0.90412401729764601266)

** The number of words in the <code>large</code> corpus: ~1.85M words
** The number of stems in the transducer: ~85.5k stems

* For MT in the direction we developed (<code>srd-eng</code>):
** WER and PER over <code>longer</code> corpus:
-------------------------------------------------------
Number of words in reference: 315
Number of words in test: 341
Number of unknown words (marked with a star) in test: 35
Percentage of unknown words: 10.26 %

Results when removing unknown-word marks (stars)
-------------------------------------------------------
Edit distance: 246
Word error rate (WER): 78.10 %
Number of position-independent correct words: 118
Position-independent word error rate (PER): 70.79 %
** The proportion of stems translated correctly in the <code>longer</code> corpus.
118/341 = 34.6%
** Trimmed coverage over <code>longer</code> and <code>large</code> corpora.
*** Over longer corpus, our coverage with the bilingual transducer is as follows (90.1%):
TOP UNKNOWN WORDS:
1 ^volùmene/*volùmene$
1 ^venit/*venit$
1 ^tenzeint/*tenzeint$
1 ^tedescu/*tedescu$
1 ^sìntesi/*sìntesi$
1 ^sincasu/*sincasu$
1 ^sambenados/*sambenados$
1 ^pressare/*pressare$
1 ^ponzo/*ponzo$
1 ^poder/*poder$
1 ^paráula/*paráula$
1 ^offerit/*offerit$
1 ^nd/*nd$
1 ^matessi/*matessi$
1 ^lu/*lu$
1 ^issoro/*issoro$
1 ^iscrittu/*iscrittu$
1 ^ischeda/*ischeda$
1 ^ghiratu/*ghiratu$
1 ^fundadores/*fundadores$
coverage: 322 / 357 (~0.90196078431372549020)
remaining unknown forms: 35
*** Coverage is 52% for bilingual transducer over large corpus: (also mostly simple words that could easily be added)

TOP UNKNOWN WORDS:
12208 ^cun/*cun$
8207 ^prus/*prus$
5205 ^o/*o$
4218 ^comente/*comente$
4100 ^fintzas/*fintzas$
3068 ^pustis/*pustis$
2658 ^annos/*annos$
2623 ^totu/*totu$
2589 ^ma/*ma$
2417 ^sua/*sua$
2376 ^parte/*parte$
2336 ^po/*po$
2250 ^Sardigna/*Sardigna$
2233 ^intre/*intre$
2120 ^ca/*ca$
2070 ^tzitade/*tzitade$
1964 ^che/*che$
1888 ^ue/*ue$
1873 ^bidda/*bidda$
1739 ^manera/*manera$
coverage: 963208 / 1863589 (~0.51685645279082458632)
** The number of tokens in <code>longer</code> and <code>large</code> corpora.
*** <code>longer</code>: 341 tokens
*** <code>large</code>: ~1.85M tokens

==10 sentences glosses and outputs==
*Note: '''These are outputs at end of lexical transfer before lexical selection and other weeks' improvements were implemented'''
{| cellpadding=5
|Sardinian sentence || intended English translation || output of srd-eng-biltrans (lexical transfer) mode || output of srd-eng (full translation) mode
|-
|1) Su sardu est una limba antica. || Sardinian is an ancient language. || ^Su<det><def><m><sg>/The<det><def><m><sg>$ ^sardu<n><m><sg>/Sardinian<n><sg>$ ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$ ^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$^.<sent>/.<sent>$^.<sent>/.<sent>$
|| #The Sardinian #be #a language #ancient
|-
|2) Pro bider s'artìculu sighire custu culligamentu. || To read the article click on this link. || ^Pro<pr>/For<pr>/To<pr>$ ^bider<vblex><inf>/read<vblex><inf>$ ^su<det><def><mf><sg>/the<det><def><mf><sg>$ ^artìculu<n><m><sg>/article<n><sg>$ ^sighire<vblex><inf>/click<vblex><inf>$ ^custu<det><dem><m><sg>/this<det><m><sg>$ ^culligamentu<n><m><sg>/link<n><sg>$^.<sent>/.<sent>$^.<sent>/.<sent>$<m><sg>$ ^culligamentu<n><m><sg>/link<n><sg>$^.<sent>/.<sent>$^.<sent>/.<sent>$
|| For read #the article click #this link.
|-
|3) Su trenu sinke fit andande. || The train was leaving. || ^Su<det><def><m><sg>/The<det><def><m><sg>$ ^trenu<n><m><sg>/train<n><sg>$ ^sinke<cnjadv>/$ ^èssere<vbser><pii><p3><sg>/be<vbser><pii><p3><sg>$ ^andare<vblex><ger>/leave<vblex><ger>/go<vblex><ger>$^.<sent>/.<sent>$^.<sent>/.<sent>$

|| #The train #be leaving.
|-
|4) Su trenu at a arrivare a sas deke. || The train will arrive at ten. || ^Su<det><def><m><sg>/The<det><def><m><sg>$ ^trenu<n><m><sg>/train<n><sg>$ ^àere<vbhaver><pri><p3><sg>/have<vbhaver><pri><p3><sg>$ ^a<pr>/at<pr>/on<pr>/to<pr>$ ^arrivare<vblex><inf>/arrive<vblex><inf>$ ^a<pr>/at<pr>/on<pr>/to<pr>$ ^su<det><def><f><pl>/the<det><def><f><pl>$ ^deke<num><mf><sp>/ten<num><mf><sp>$^.<sent>/.<sent>$^.<sent>/.<sent>$
|| #The train #have at arrive at #the #ten.
|-
|5) Su trenu devet arrivare a sas deke. || The train should arrive at ten. || ^Su<det><def><m><sg>/The<det><def><m><sg>$ ^trenu<n><m><sg>/train<n><sg>$ ^dèvere<vblex><pri><p3><sg>/shall<vbmod><pri><p3><sg>$ ^arrivare<vblex><inf>/arrive<vblex><inf>$ ^a<pr>/at<pr>/on<pr>/to<pr>$ ^su<det><def><f><pl>/the<det><def><f><pl>$ ^deke<num><mf><sp>/ten<num><mf><sp>$^.<sent>/.<sent>$^.<sent>/.<sent>$
|| #The train #shall arrive at #the #ten.
|-
|6) T'appo natu ki su trenu devíat arrivare a sas deke. || I told you that the train would arrive at ten. || ^Ti<prn><pro><p2><mf><sg>/You<prn><pro><p2><mf><sg>$ ^àere<vbhaver><pri><p1><sg>/have<vbhaver><pri><p1><sg>$ ^nàrrere<vblex><pp><m><sg>/tell<vblex><pp><m><sg>$ ^chi<cnjsub>/that<cnjsub>$ ^su<det><def><m><sg>/the<det><def><m><sg>$ ^trenu<n><m><sg>/train<n><sg>$ ^dèvere<vblex><pii><p3><sg>/shall<vbmod><pii><p3><sg>$ ^arrivare<vblex><inf>/arrive<vblex><inf>$ ^a<pr>/at<pr>/on<pr>/to<pr>$ ^su<det><def><f><pl>/the<det><def><f><pl>$ ^deke<num><mf><sp>/ten<num><mf><sp>$^.<sent>/.<sent>$^.<sent>/.<sent>$
|| #You #have #tell that #the train #shall arrive at #the #ten.
|-
|7) No'isco si at a pròere cras. || I do not know if it will rain tomorrow. || ^No<adv>/Not<adv>$'^iscoare<vblex><pri><p1><sg>/know<vblex><pri><p1><sg>$ ^si<cnjsub>/if<cnjsub>$ ^àere<vbhaver><pri><p3><sg>/have<vbhaver><pri><p3><sg>$ ^a<pr>/at<pr>/on<pr>/to<pr>$ ^pròere<vblex><inf>/rain<vblex><inf>$ ^cras<adv>/tomorrow<adv>$^.<sent>/.<sent>$
|| Not'#know if #have at rain tomorrow

|-
|8) Una de sas berbekes est maláida. || One of the sheep is sick. || ^Unu<num><f><sp>/One<num><f><sp>$ ^de<pr>/to<pr>/of<pr>$ ^su<det><def><f><pl>/the<det><def><f><pl>$ ^berbeke<n><f><pl>/sheep<n><pl>$ ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$ ^malàidu<adj><f><sg>/sick<adj><f><sg>$^.<sent>/.<sent>$
|| #One to #the sheep #be #sick

|-
|9) Appo pèrditu duos de sos libros meos. || I have lost two of my books. || ^Àere<vbhaver><pri><p1><sg>/Have<vbhaver><pri><p1><sg>$ ^pèrdere<vblex><pp><m><sg>/lose<vblex><pp><m><sg>$ ^duos<num><m><sp>/two<num><m><sp>$ ^de<pr>/to<pr>/of<pr>$ ^su<det><def><m><pl>/the<det><def><m><pl>$ ^libru<n><m><pl>/book<n><pl>$ ^meu<prn><pos><m><pl>/my<prn><pos><m><pl>$^.<sent>/.<sent>$

|| #Have #lose #two to #the books #my

|-
|10) M'an natu ki su trenu devíat arrivare a sas nove. || They told me that the train was supposed to arrive at nine. || ^Mi<prn><pro><p1><mf><sg>/I<prn><pro><p1><mf><sg>$ ^àere<vbhaver><pri><p3><pl>/have<vbhaver><pri><p3><pl>$ ^nàrrere<vblex><pp><m><sg>/tell<vblex><pp><m><sg>$ ^chi<cnjsub>/that<cnjsub>$ ^su<det><def><m><sg>/the<det><def><m><sg>$ ^trenu<n><m><sg>/train<n><sg>$ ^dèvere<vblex><pii><p3><sg>/shall<vbmod><pii><p3><sg>$ ^arrivare<vblex><inf>/arrive<vblex><inf>$ ^a<pr>/at<pr>/on<pr>/to<pr>$ ^su<det><def><f><pl>/the<det><def><f><pl>$ ^nove<num><mf><sp>/nine<num><mf><sp>$^.<sent>/.<sent>$
|| #I #have #tell that #the train #shall arrive at #the #nine
|
|}

==expanding lexicon==

{| cellpadding=5
|medas || many || <adj>
|-https://wikis.swarthmore.edu/ling073/index.php?title=Sardinian_and_English&action=edit
|piseddas || girls || <n><pl>
|-
|sun || they are || <v>
|-
|bennidas || to come (home) || <v><pp><fpl>
|-
|balladu || to dance || <v><pp>
|-
|cantaiat || to sing || <v><sg3>
|-
|sos/sa || the || <det>
|-
|piattos || plates || <n><pl>
|-
|mesa || table || <n><sg>
|-
|bi/b' || N/A || <cl>
|-
|problemas || problems || <n><pl>
|-
|unu || one/a || <adj>/<det>
|-
|ube || where || <adv>
|-
|mortu || dead || <v><pp>
|-
|sordatos || soldiers || <n><pl>
|-
|tenimus || we have || <v><pl1>
|-
|frores || flowers || <n><pl>
|-
|keret || to be necessary || <v><sg3>
|-
|mancat || to be missing || <v><sg3>
|-
|ovos || eggs || <n><pl>
|-
|danca || meadow || <n>
|-
|ortu || orchard || <n>
|-
|frade || brother || <n>
|-
|fizza || daughter || <n>
|-
|re || king || <n>
|-
|ora || hour || <n>
|-
|subra || above/on || <prep>
|-
|a || to/at || <prep>
|-
|cumintzos || origins || <n><pl>
|-
|e || and || <conj>
|-
|andamentu || evolution || <n>
|-
|istòricu || historical || <adj>
|-
|de || of/to || <prep>
|-
|sa || the || <det>
|-
|poesia || poetry || <n>
|-
|a bolu || improvised || <adj> (a bolu = improvised, on the fly)
|-
|in || in || <prep>
|-
|sardu || Sardinian || <n>
|-
|logudoresu || Logudorese || <adj>
|-
|non || not || <adv>
|-
|ischit || known || <v><pp>
|-
|meda || much || <adv>
|-
|custu || this || <det><prox>
|-
|artìculu || article || <n>
|-
|chircat || tries || <v><sg3>
|-
|bogare || to bring out || <v>
|-
|pizu || surface || <n> (bogare a pizu = to shed light on, to bring to the surface; see complicated translations of bogare: [http://vocabolariocasu.isresardegna.it/index.php?key=b&int=0&lemmi=cerca&codice=b1264000 here])
|-
|ammentos || memories || <n><pl>
|-
|ammentu || memory || <n>
|-
|ammentare || to remember || <v>
|-
|documentados || documented || <adj>
|-
|si || [null] || <> -- reflexive
|-
|primas || first || <adj>
|-
|disputas || competitions || <n><pl>
|-
|primas || first || <adj>
|-
|tra || between || <prep>
|-
|poetes || poets || <n><pl>
|-
|cale || which || <prn><rel>
|-
|esserent || were || <v> past imperfect 3rd person plural
|-
|règulas || rules, modalities || <n><pl>
|-
|su || the || <det>
|-
|cunfruntu || confrontation || <n>
|-
|sende || being || <v><ger>
|-
|una || a/one || <art>/<adj>
|-
|chirca || research || <n>
|-
|andera || ongoing/progressive || <adj>
|-
|testu || text || <n>
|-
|diat || [null] || <subj><sg3>
|-
|poder || to be able to || <v><inf>
|-
|aer || to have || <v><inf> (also hàere or àere)
|-
|mudonzos || modifications || <n><pl>
|-
|mudonzos || modifications || <n><pl>
|-
|novas || new || <adj><pl>
|-
|noas || data || <n><pl>
|-
|Pro || to || <prep> <-- keep this in mind for lexical selection (to)
|-
|bider || to read || <v><inf>
|-
|artìculu || article || <n>
|-
|sighire || click on || <v><inf>
|-
|intrare || enter || <v><inf>
|-
|desizadu || desired || <adj>
|-
|trenu || train || <n>
|-
|sinke || [null] || <foc>
|-
|fit || was || <v><imp><sg3>
|-
|andande || leaving || <v><ger>
|-
|at || it will || <>
|-
|sas || the || <det>
|-
|deke || ten || <n>
|-
|devet || should || <adv>
|-
|deke || ten || <adj>
|-
|appo || I have || <v><sg1>
|-
|natu || told || <v><pp>
|-
|próere || to rain || <v><inf>
|-
|arrivare || to arrive || <v><inf>
|-
|isco || I know || <v><sg1>
|-
|si || if || <conj>
|-
|ki || that || <conj>
|-
|cras || tomorrow || <adv>
|-
|meos || my || <pos>
|-
|andatos || gone || <adj><pl>
|
|}

===glosses===

Cando so arrivatu a s'istazione, su trenu sink'andaiat

'when I arrived at the station, the train was leaving'

Su trenu sinke fit andande

'The train was leaving"

Su trenu at a arrivare a sas deke

'The train will arrive at ten o'clock'

Su trenu devet arrivare a sas deke

'The train is supposed to arrive at ten o'clock'

T'appo natu ki su trenu diat arrivare a sas deke

'I told you that the train would arrive at ten o'clock'

M'an natu ki su trenu devíat arrivare a sas nove

'They told me that the train was supposed to arrive at nine'

At a próere cras

'It will rain tomorrow'

Devet próere cras

'it is supposed to rain tomorrow'

At a próere cras? Si emmo abbarramus in domo, ma su nono andamus a mare

'Will it rain tomorrow? If so we shall stay at homr, buy if not we will go to the sea'

No'isco si at a próere cras

'I do to know whether it will rain tomorrow'

Una de sas berbekes est maláida

'one of the sheep is sick'

Appo pèrditu duos de sos libros meos

'I have lost two of my books'

Metas de custas pitzinnas sun galanas

'Many of these girls are pretty'

Una pitzinna meta bella

'a very beautiful girl'

Cussas duas bravas pitzinnas

'those two good girls'

unu better cane bellu

'a huge beautiful dog'

un'átteru bette cane

'another huge dog'

Sun andatos a Frantza

'they went to France'

Est ghiratu dae Corsica

'He returned from Corsica'

Connnosco bene sa Frantza

"i know France well'

Custu libru est iscrittu in tedescu

'This book is written in German'

Cussus paráula venit dae su catalanu

'This word comes from Catalan'

Su sardu est una limba antica

'Sardinian is an ancient language'

Appo mandicatu casu

'I ate cheese'

Laura est toddende frores

'Laura is picking flowers'

De frores non nd'appo tódditu

'I did not pick any flowers'

No'amus comporatu pane

'We did not buy bread'

Mandico sa pasta kin casu

'I ate pasta with cheese'

Tres sórrikes an mandicatu tottu su casu

'Three mice ate all the cheese'

semus ponnende vinu in ampullas

'We are putting wine in bottles'

lettu meu esr

'It is my bed'

No'appo lessu libru perunu

'i did not read any book'

Sos k'an furatu si dinari at a èssere punitos

'The people who stole the money will be punished'

Appo invitat sos de Juanne

'I invited Jon's family'

Cussa pinna est sa mea

'That pen is mine'

Cudda mákkina est sa de Juanne

'That car is John's'

Custa ricca at datu mili francos a su vetzu

'This rich woman gave a thousand lira to the old man'

Su guvernu devíat dare ua pensione a dondzi vetzu

'The government should give a pension to every old person'

==External Resources==

*Github repository for [https://github.com/apertium/apertium-srd Sardinian transducer] (and our [https://github.swarthmore.edu/Ling073-sp23/ling073-srd clone])
*Github repository for [https://github.com/apertium/apertium-eng English transducer]
*[https://www.limbasardasudsardigna.it/sar/images/Documenti/Didatica_e_Ainas/Ditzion%C3%A0riu%20Universale%20Rubattu.pdf Dictionary pdf]
*[http://ditzionariu.sardegnacultura.it/it/ Online official dictionary]
*[https://it.glosbe.com/sc/it Web-based machine translator]
*[http://vocabolariocasu.isresardegna.it/index.php?key=a&int=0&lemmi=cerca Sardinian-Italian web-based dictionary]
*[http://www.sardegnadigitallibrary.it/mmt/fullsize/2009050512495700047.pdf 1931 pdf with select translations]
*[https://onlinelibrary.wiley.com/doi/epdf/10.1111/j.0079-1636.2004.00130.x Definiteness effects: evidence from Sardinian]
*[https://www.icongrouponline.com/en/Detail/dictionary/049783698X/Webster%27s+Sardinian+-+English+Thesaurus+Dictionary: Webster's Sardinian English Thesaurus Dictionary]
*[https://www.academia.edu/15320922/Dizionario_della_lingua_Sarda_Vol_2 Italian-Sardinian Dictionary]
*[https://archive.org/details/vocabolariosardo00spanuoft/page/n361/mode/2up Old but extensive Sardo-Italian and vice versa dictionary]
*[https://limbasardasudsardigna.it/sar/images/Documenti/Didatica_e_Ainas/Vocabolariu_Sardu_Italianu_Spano.pdf nice Sardo-Italiano dictionary pdf]
*[http://www.fontesarda.it/sr/sr0045.htm Conjugations of "to have" in Sardinian]
*[https://sinnainotizie.com/2015/03/07/lezioni-di-grammatica-sardo-campidanese-undicesima-lezione-su-verbu-ai-aere/ Whole Sardinian grammar page about conjugations of to have all written in Sardinian language!]
*Sardinian grammar:[https://www.limbasardasudsardigna.it/sar/images/Documenti/Didatica_e_Ainas/grammatiga_sardo%20campidanese%20A.LEPORI.pdf pdf]
[[Category:Sp23_TranslationPairs]],[[Category:Sardinian]],[[Category:English]]

Sardinian and English

2023-05-05T19:41:41Z

Rorlija1: /* Final evaluation */

=Resources for Machine Translation from Sardinian to English=

==Developed Resources==
*[https://github.swarthmore.edu/Ling073-sp23/ling073-srd-eng-corpus Parallel corpus git repo].
*:Lines 1-8 from [http://maxia-mail.doomby.com/ this website].
*[https://github.swarthmore.edu/Ling073-sp23/ling073-srd-eng Git repo for language pair]
*[https://github.swarthmore.edu/Ling073-sp23/ling073-srd Git repo for Sardinian]
*[https://github.com/apertium/apertium-eng Forked git repo for English]
*[https://wikis.swarthmore.edu/ling073/Sardinian_and_English/Lexical_selection#srd_.E2.86.92_eng Lexical selection wiki]
*[https://wikis.swarthmore.edu/ling073/Sardinian_and_English/Contrastive_Grammar#Differences_in_parse_and_corresponding_examples Contrastive grammar wiki]
*[https://wikis.swarthmore.edu/ling073/Sardinian_and_English/Structural_transfer Structural transfer wiki]

==srd → eng evaluation==
*coverage of monolingual Sardinian transducer on srd.sentences.txt:
Number of tokenised words in the corpus: 262
Coverage: 94.66%
*coverage of bilingual transducer on srd.sentences
Number of tokenised words in the corpus: 266
Coverage: 85.71%

==Additions for polished RBMT system==
*Over 100 new stems to bilingual dictionary
*:(now we have 172 total entries in the .dix file)
*4 sets of lexical selection rules
*:(now we have rules that solve 5 problems in total)
*3 items from contrastive grammar implemented in transfer rules
*:(now we have rules that implement 4 total items)

==Final evaluation==
* For the monolingual transducer:
** Precision and recall against srd.sentences.txt (1314 char):
Totals: 145 forms, 417 tp, 0 fp, 0 tn, 11 fn
Precision: 100.00000%
Recall: 97.42991%
** Coverage over the <code>large</code> corpus:
*** 90.4% with monolingual transducer: (mostly simple words that could easily be added)

TOP UNKNOWN WORDS:
2336 ^po/*po$
1275 ^che/*che$
448 ^i/*i$
387 ^norte/*norte$
377 ^The/*The$
353 ^of/*of$
297 ^poi/*poi$
269 ^del/*del$
241 ^the/*the$
235 ^da/*da$
215 ^ch/*ch$
211 ^Il/*Il$
205 ^chentza/*chentza$
200 ^br/*br$
199 ^Arbaree/*Arbaree$
197 ^della/*della$
192 ^stètiu/*stètiu$
165 ^ddoi/*ddoi$
154 ^B/*B$
145 ^Norte/*Norte$
coverage: 1648134 / 1822907 (~0.90412401729764601266)

*** 52% for bilingual transducer: (also mostly simple words that could easily be added)

TOP UNKNOWN WORDS:
12208 ^cun/*cun$
8207 ^prus/*prus$
5205 ^o/*o$
4218 ^comente/*comente$
4100 ^fintzas/*fintzas$
3068 ^pustis/*pustis$
2658 ^annos/*annos$
2623 ^totu/*totu$
2589 ^ma/*ma$
2417 ^sua/*sua$
2376 ^parte/*parte$
2336 ^po/*po$
2250 ^Sardigna/*Sardigna$
2233 ^intre/*intre$
2120 ^ca/*ca$
2070 ^tzitade/*tzitade$
1964 ^che/*che$
1888 ^ue/*ue$
1873 ^bidda/*bidda$
1739 ^manera/*manera$
coverage: 963208 / 1863589 (~0.51685645279082458632)

** The number of words in the <code>large</code> corpus: ~1.85M words
** The number of stems in the transducer: ~85.5k stems

* For MT in the direction we developed (<code>srd-eng</code>):
** WER and PER over <code>longer</code> corpus:
-------------------------------------------------------
Number of words in reference: 315
Number of words in test: 341
Number of unknown words (marked with a star) in test: 35
Percentage of unknown words: 10.26 %

Results when removing unknown-word marks (stars)
-------------------------------------------------------
Edit distance: 246
Word error rate (WER): 78.10 %
Number of position-independent correct words: 118
Position-independent word error rate (PER): 70.79 %
** The proportion of stems translated correctly in the <code>longer</code> corpus.
118/341 = 34.6%
** Trimmed coverage over <code>longer</code> and <code>large</code> corpora.
***Over longer corpus, our coverage with the bilingual transducer is as follows (90.1%):
TOP UNKNOWN WORDS:
1 ^volùmene/*volùmene$
1 ^venit/*venit$
1 ^tenzeint/*tenzeint$
1 ^tedescu/*tedescu$
1 ^sìntesi/*sìntesi$
1 ^sincasu/*sincasu$
1 ^sambenados/*sambenados$
1 ^pressare/*pressare$
1 ^ponzo/*ponzo$
1 ^poder/*poder$
1 ^paráula/*paráula$
1 ^offerit/*offerit$
1 ^nd/*nd$
1 ^matessi/*matessi$
1 ^lu/*lu$
1 ^issoro/*issoro$
1 ^iscrittu/*iscrittu$
1 ^ischeda/*ischeda$
1 ^ghiratu/*ghiratu$
1 ^fundadores/*fundadores$
coverage: 322 / 357 (~0.90196078431372549020)
remaining unknown forms: 35

** The number of tokens in <code>longer</code> and <code>large</code> corpora.
*** <code>longer</code>: 341 tokens
*** <code>large</code>: ~1.85M tokens

==10 sentences glosses and outputs==
*Note: '''These are outputs at end of lexical transfer before lexical selection and other weeks' improvements were implemented'''
{| cellpadding=5
|Sardinian sentence || intended English translation || output of srd-eng-biltrans (lexical transfer) mode || output of srd-eng (full translation) mode
|-
|1) Su sardu est una limba antica. || Sardinian is an ancient language. || ^Su<det><def><m><sg>/The<det><def><m><sg>$ ^sardu<n><m><sg>/Sardinian<n><sg>$ ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$ ^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$^.<sent>/.<sent>$^.<sent>/.<sent>$
|| #The Sardinian #be #a language #ancient
|-
|2) Pro bider s'artìculu sighire custu culligamentu. || To read the article click on this link. || ^Pro<pr>/For<pr>/To<pr>$ ^bider<vblex><inf>/read<vblex><inf>$ ^su<det><def><mf><sg>/the<det><def><mf><sg>$ ^artìculu<n><m><sg>/article<n><sg>$ ^sighire<vblex><inf>/click<vblex><inf>$ ^custu<det><dem><m><sg>/this<det><m><sg>$ ^culligamentu<n><m><sg>/link<n><sg>$^.<sent>/.<sent>$^.<sent>/.<sent>$<m><sg>$ ^culligamentu<n><m><sg>/link<n><sg>$^.<sent>/.<sent>$^.<sent>/.<sent>$
|| For read #the article click #this link.
|-
|3) Su trenu sinke fit andande. || The train was leaving. || ^Su<det><def><m><sg>/The<det><def><m><sg>$ ^trenu<n><m><sg>/train<n><sg>$ ^sinke<cnjadv>/$ ^èssere<vbser><pii><p3><sg>/be<vbser><pii><p3><sg>$ ^andare<vblex><ger>/leave<vblex><ger>/go<vblex><ger>$^.<sent>/.<sent>$^.<sent>/.<sent>$

|| #The train #be leaving.
|-
|4) Su trenu at a arrivare a sas deke. || The train will arrive at ten. || ^Su<det><def><m><sg>/The<det><def><m><sg>$ ^trenu<n><m><sg>/train<n><sg>$ ^àere<vbhaver><pri><p3><sg>/have<vbhaver><pri><p3><sg>$ ^a<pr>/at<pr>/on<pr>/to<pr>$ ^arrivare<vblex><inf>/arrive<vblex><inf>$ ^a<pr>/at<pr>/on<pr>/to<pr>$ ^su<det><def><f><pl>/the<det><def><f><pl>$ ^deke<num><mf><sp>/ten<num><mf><sp>$^.<sent>/.<sent>$^.<sent>/.<sent>$
|| #The train #have at arrive at #the #ten.
|-
|5) Su trenu devet arrivare a sas deke. || The train should arrive at ten. || ^Su<det><def><m><sg>/The<det><def><m><sg>$ ^trenu<n><m><sg>/train<n><sg>$ ^dèvere<vblex><pri><p3><sg>/shall<vbmod><pri><p3><sg>$ ^arrivare<vblex><inf>/arrive<vblex><inf>$ ^a<pr>/at<pr>/on<pr>/to<pr>$ ^su<det><def><f><pl>/the<det><def><f><pl>$ ^deke<num><mf><sp>/ten<num><mf><sp>$^.<sent>/.<sent>$^.<sent>/.<sent>$
|| #The train #shall arrive at #the #ten.
|-
|6) T'appo natu ki su trenu devíat arrivare a sas deke. || I told you that the train would arrive at ten. || ^Ti<prn><pro><p2><mf><sg>/You<prn><pro><p2><mf><sg>$ ^àere<vbhaver><pri><p1><sg>/have<vbhaver><pri><p1><sg>$ ^nàrrere<vblex><pp><m><sg>/tell<vblex><pp><m><sg>$ ^chi<cnjsub>/that<cnjsub>$ ^su<det><def><m><sg>/the<det><def><m><sg>$ ^trenu<n><m><sg>/train<n><sg>$ ^dèvere<vblex><pii><p3><sg>/shall<vbmod><pii><p3><sg>$ ^arrivare<vblex><inf>/arrive<vblex><inf>$ ^a<pr>/at<pr>/on<pr>/to<pr>$ ^su<det><def><f><pl>/the<det><def><f><pl>$ ^deke<num><mf><sp>/ten<num><mf><sp>$^.<sent>/.<sent>$^.<sent>/.<sent>$
|| #You #have #tell that #the train #shall arrive at #the #ten.
|-
|7) No'isco si at a pròere cras. || I do not know if it will rain tomorrow. || ^No<adv>/Not<adv>$'^iscoare<vblex><pri><p1><sg>/know<vblex><pri><p1><sg>$ ^si<cnjsub>/if<cnjsub>$ ^àere<vbhaver><pri><p3><sg>/have<vbhaver><pri><p3><sg>$ ^a<pr>/at<pr>/on<pr>/to<pr>$ ^pròere<vblex><inf>/rain<vblex><inf>$ ^cras<adv>/tomorrow<adv>$^.<sent>/.<sent>$
|| Not'#know if #have at rain tomorrow

|-
|8) Una de sas berbekes est maláida. || One of the sheep is sick. || ^Unu<num><f><sp>/One<num><f><sp>$ ^de<pr>/to<pr>/of<pr>$ ^su<det><def><f><pl>/the<det><def><f><pl>$ ^berbeke<n><f><pl>/sheep<n><pl>$ ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$ ^malàidu<adj><f><sg>/sick<adj><f><sg>$^.<sent>/.<sent>$
|| #One to #the sheep #be #sick

|-
|9) Appo pèrditu duos de sos libros meos. || I have lost two of my books. || ^Àere<vbhaver><pri><p1><sg>/Have<vbhaver><pri><p1><sg>$ ^pèrdere<vblex><pp><m><sg>/lose<vblex><pp><m><sg>$ ^duos<num><m><sp>/two<num><m><sp>$ ^de<pr>/to<pr>/of<pr>$ ^su<det><def><m><pl>/the<det><def><m><pl>$ ^libru<n><m><pl>/book<n><pl>$ ^meu<prn><pos><m><pl>/my<prn><pos><m><pl>$^.<sent>/.<sent>$

|| #Have #lose #two to #the books #my

|-
|10) M'an natu ki su trenu devíat arrivare a sas nove. || They told me that the train was supposed to arrive at nine. || ^Mi<prn><pro><p1><mf><sg>/I<prn><pro><p1><mf><sg>$ ^àere<vbhaver><pri><p3><pl>/have<vbhaver><pri><p3><pl>$ ^nàrrere<vblex><pp><m><sg>/tell<vblex><pp><m><sg>$ ^chi<cnjsub>/that<cnjsub>$ ^su<det><def><m><sg>/the<det><def><m><sg>$ ^trenu<n><m><sg>/train<n><sg>$ ^dèvere<vblex><pii><p3><sg>/shall<vbmod><pii><p3><sg>$ ^arrivare<vblex><inf>/arrive<vblex><inf>$ ^a<pr>/at<pr>/on<pr>/to<pr>$ ^su<det><def><f><pl>/the<det><def><f><pl>$ ^nove<num><mf><sp>/nine<num><mf><sp>$^.<sent>/.<sent>$
|| #I #have #tell that #the train #shall arrive at #the #nine
|
|}

==expanding lexicon==

{| cellpadding=5
|medas || many || <adj>
|-https://wikis.swarthmore.edu/ling073/index.php?title=Sardinian_and_English&action=edit
|piseddas || girls || <n><pl>
|-
|sun || they are || <v>
|-
|bennidas || to come (home) || <v><pp><fpl>
|-
|balladu || to dance || <v><pp>
|-
|cantaiat || to sing || <v><sg3>
|-
|sos/sa || the || <det>
|-
|piattos || plates || <n><pl>
|-
|mesa || table || <n><sg>
|-
|bi/b' || N/A || <cl>
|-
|problemas || problems || <n><pl>
|-
|unu || one/a || <adj>/<det>
|-
|ube || where || <adv>
|-
|mortu || dead || <v><pp>
|-
|sordatos || soldiers || <n><pl>
|-
|tenimus || we have || <v><pl1>
|-
|frores || flowers || <n><pl>
|-
|keret || to be necessary || <v><sg3>
|-
|mancat || to be missing || <v><sg3>
|-
|ovos || eggs || <n><pl>
|-
|danca || meadow || <n>
|-
|ortu || orchard || <n>
|-
|frade || brother || <n>
|-
|fizza || daughter || <n>
|-
|re || king || <n>
|-
|ora || hour || <n>
|-
|subra || above/on || <prep>
|-
|a || to/at || <prep>
|-
|cumintzos || origins || <n><pl>
|-
|e || and || <conj>
|-
|andamentu || evolution || <n>
|-
|istòricu || historical || <adj>
|-
|de || of/to || <prep>
|-
|sa || the || <det>
|-
|poesia || poetry || <n>
|-
|a bolu || improvised || <adj> (a bolu = improvised, on the fly)
|-
|in || in || <prep>
|-
|sardu || Sardinian || <n>
|-
|logudoresu || Logudorese || <adj>
|-
|non || not || <adv>
|-
|ischit || known || <v><pp>
|-
|meda || much || <adv>
|-
|custu || this || <det><prox>
|-
|artìculu || article || <n>
|-
|chircat || tries || <v><sg3>
|-
|bogare || to bring out || <v>
|-
|pizu || surface || <n> (bogare a pizu = to shed light on, to bring to the surface; see complicated translations of bogare: [http://vocabolariocasu.isresardegna.it/index.php?key=b&int=0&lemmi=cerca&codice=b1264000 here])
|-
|ammentos || memories || <n><pl>
|-
|ammentu || memory || <n>
|-
|ammentare || to remember || <v>
|-
|documentados || documented || <adj>
|-
|si || [null] || <> -- reflexive
|-
|primas || first || <adj>
|-
|disputas || competitions || <n><pl>
|-
|primas || first || <adj>
|-
|tra || between || <prep>
|-
|poetes || poets || <n><pl>
|-
|cale || which || <prn><rel>
|-
|esserent || were || <v> past imperfect 3rd person plural
|-
|règulas || rules, modalities || <n><pl>
|-
|su || the || <det>
|-
|cunfruntu || confrontation || <n>
|-
|sende || being || <v><ger>
|-
|una || a/one || <art>/<adj>
|-
|chirca || research || <n>
|-
|andera || ongoing/progressive || <adj>
|-
|testu || text || <n>
|-
|diat || [null] || <subj><sg3>
|-
|poder || to be able to || <v><inf>
|-
|aer || to have || <v><inf> (also hàere or àere)
|-
|mudonzos || modifications || <n><pl>
|-
|mudonzos || modifications || <n><pl>
|-
|novas || new || <adj><pl>
|-
|noas || data || <n><pl>
|-
|Pro || to || <prep> <-- keep this in mind for lexical selection (to)
|-
|bider || to read || <v><inf>
|-
|artìculu || article || <n>
|-
|sighire || click on || <v><inf>
|-
|intrare || enter || <v><inf>
|-
|desizadu || desired || <adj>
|-
|trenu || train || <n>
|-
|sinke || [null] || <foc>
|-
|fit || was || <v><imp><sg3>
|-
|andande || leaving || <v><ger>
|-
|at || it will || <>
|-
|sas || the || <det>
|-
|deke || ten || <n>
|-
|devet || should || <adv>
|-
|deke || ten || <adj>
|-
|appo || I have || <v><sg1>
|-
|natu || told || <v><pp>
|-
|próere || to rain || <v><inf>
|-
|arrivare || to arrive || <v><inf>
|-
|isco || I know || <v><sg1>
|-
|si || if || <conj>
|-
|ki || that || <conj>
|-
|cras || tomorrow || <adv>
|-
|meos || my || <pos>
|-
|andatos || gone || <adj><pl>
|
|}

===glosses===

Cando so arrivatu a s'istazione, su trenu sink'andaiat

'when I arrived at the station, the train was leaving'

Su trenu sinke fit andande

'The train was leaving"

Su trenu at a arrivare a sas deke

'The train will arrive at ten o'clock'

Su trenu devet arrivare a sas deke

'The train is supposed to arrive at ten o'clock'

T'appo natu ki su trenu diat arrivare a sas deke

'I told you that the train would arrive at ten o'clock'

M'an natu ki su trenu devíat arrivare a sas nove

'They told me that the train was supposed to arrive at nine'

At a próere cras

'It will rain tomorrow'

Devet próere cras

'it is supposed to rain tomorrow'

At a próere cras? Si emmo abbarramus in domo, ma su nono andamus a mare

'Will it rain tomorrow? If so we shall stay at homr, buy if not we will go to the sea'

No'isco si at a próere cras

'I do to know whether it will rain tomorrow'

Una de sas berbekes est maláida

'one of the sheep is sick'

Appo pèrditu duos de sos libros meos

'I have lost two of my books'

Metas de custas pitzinnas sun galanas

'Many of these girls are pretty'

Una pitzinna meta bella

'a very beautiful girl'

Cussas duas bravas pitzinnas

'those two good girls'

unu better cane bellu

'a huge beautiful dog'

un'átteru bette cane

'another huge dog'

Sun andatos a Frantza

'they went to France'

Est ghiratu dae Corsica

'He returned from Corsica'

Connnosco bene sa Frantza

"i know France well'

Custu libru est iscrittu in tedescu

'This book is written in German'

Cussus paráula venit dae su catalanu

'This word comes from Catalan'

Su sardu est una limba antica

'Sardinian is an ancient language'

Appo mandicatu casu

'I ate cheese'

Laura est toddende frores

'Laura is picking flowers'

De frores non nd'appo tódditu

'I did not pick any flowers'

No'amus comporatu pane

'We did not buy bread'

Mandico sa pasta kin casu

'I ate pasta with cheese'

Tres sórrikes an mandicatu tottu su casu

'Three mice ate all the cheese'

semus ponnende vinu in ampullas

'We are putting wine in bottles'

lettu meu esr

'It is my bed'

No'appo lessu libru perunu

'i did not read any book'

Sos k'an furatu si dinari at a èssere punitos

'The people who stole the money will be punished'

Appo invitat sos de Juanne

'I invited Jon's family'

Cussa pinna est sa mea

'That pen is mine'

Cudda mákkina est sa de Juanne

'That car is John's'

Custa ricca at datu mili francos a su vetzu

'This rich woman gave a thousand lira to the old man'

Su guvernu devíat dare ua pensione a dondzi vetzu

'The government should give a pension to every old person'

==External Resources==

*Github repository for [https://github.com/apertium/apertium-srd Sardinian transducer] (and our [https://github.swarthmore.edu/Ling073-sp23/ling073-srd clone])
*Github repository for [https://github.com/apertium/apertium-eng English transducer]
*[https://www.limbasardasudsardigna.it/sar/images/Documenti/Didatica_e_Ainas/Ditzion%C3%A0riu%20Universale%20Rubattu.pdf Dictionary pdf]
*[http://ditzionariu.sardegnacultura.it/it/ Online official dictionary]
*[https://it.glosbe.com/sc/it Web-based machine translator]
*[http://vocabolariocasu.isresardegna.it/index.php?key=a&int=0&lemmi=cerca Sardinian-Italian web-based dictionary]
*[http://www.sardegnadigitallibrary.it/mmt/fullsize/2009050512495700047.pdf 1931 pdf with select translations]
*[https://onlinelibrary.wiley.com/doi/epdf/10.1111/j.0079-1636.2004.00130.x Definiteness effects: evidence from Sardinian]
*[https://www.icongrouponline.com/en/Detail/dictionary/049783698X/Webster%27s+Sardinian+-+English+Thesaurus+Dictionary: Webster's Sardinian English Thesaurus Dictionary]
*[https://www.academia.edu/15320922/Dizionario_della_lingua_Sarda_Vol_2 Italian-Sardinian Dictionary]
*[https://archive.org/details/vocabolariosardo00spanuoft/page/n361/mode/2up Old but extensive Sardo-Italian and vice versa dictionary]
*[https://limbasardasudsardigna.it/sar/images/Documenti/Didatica_e_Ainas/Vocabolariu_Sardu_Italianu_Spano.pdf nice Sardo-Italiano dictionary pdf]
*[http://www.fontesarda.it/sr/sr0045.htm Conjugations of "to have" in Sardinian]
*[https://sinnainotizie.com/2015/03/07/lezioni-di-grammatica-sardo-campidanese-undicesima-lezione-su-verbu-ai-aere/ Whole Sardinian grammar page about conjugations of to have all written in Sardinian language!]
*Sardinian grammar:[https://www.limbasardasudsardigna.it/sar/images/Documenti/Didatica_e_Ainas/grammatiga_sardo%20campidanese%20A.LEPORI.pdf pdf]
[[Category:Sp23_TranslationPairs]],[[Category:Sardinian]],[[Category:English]]

Sardinian and English

2023-05-05T19:19:07Z

Rorlija1: /* Final evaluation */

=Resources for Machine Translation from Sardinian to English=

==Developed Resources==
*[https://github.swarthmore.edu/Ling073-sp23/ling073-srd-eng-corpus Parallel corpus git repo].
*:Lines 1-8 from [http://maxia-mail.doomby.com/ this website].
*[https://github.swarthmore.edu/Ling073-sp23/ling073-srd-eng Git repo for language pair]
*[https://github.swarthmore.edu/Ling073-sp23/ling073-srd Git repo for Sardinian]
*[https://github.com/apertium/apertium-eng Forked git repo for English]
*[https://wikis.swarthmore.edu/ling073/Sardinian_and_English/Lexical_selection#srd_.E2.86.92_eng Lexical selection wiki]
*[https://wikis.swarthmore.edu/ling073/Sardinian_and_English/Contrastive_Grammar#Differences_in_parse_and_corresponding_examples Contrastive grammar wiki]
*[https://wikis.swarthmore.edu/ling073/Sardinian_and_English/Structural_transfer Structural transfer wiki]

==srd → eng evaluation==
*coverage of monolingual Sardinian transducer on srd.sentences.txt:
Number of tokenised words in the corpus: 262
Coverage: 94.66%
*coverage of bilingual transducer on srd.sentences
Number of tokenised words in the corpus: 266
Coverage: 85.71%

==Additions for polished RBMT system==
*Over 100 new stems to bilingual dictionary
*:(now we have 172 total entries in the .dix file)
*4 sets of lexical selection rules
*:(now we have rules that solve 5 problems in total)
*3 items from contrastive grammar implemented in transfer rules
*:(now we have rules that implement 4 total items)

==Final evaluation==
* For the monolingual transducer:
** Updated precision and recall against the (updated) <code>eval.test</code> and <code>eval.gold</code> files
** Coverage over the <code>large</code> corpus:
***90.4% with monolingual transducer: (mostly simple words that could easily be added)

TOP UNKNOWN WORDS:
2336 ^po/*po$
1275 ^che/*che$
448 ^i/*i$
387 ^norte/*norte$
377 ^The/*The$
353 ^of/*of$
297 ^poi/*poi$
269 ^del/*del$
241 ^the/*the$
235 ^da/*da$
215 ^ch/*ch$
211 ^Il/*Il$
205 ^chentza/*chentza$
200 ^br/*br$
199 ^Arbaree/*Arbaree$
197 ^della/*della$
192 ^stètiu/*stètiu$
165 ^ddoi/*ddoi$
154 ^B/*B$
145 ^Norte/*Norte$
coverage: 1648134 / 1822907 (~0.90412401729764601266)

***52% for bilingual transducer: (also mostly simple words that could easily be added)

TOP UNKNOWN WORDS:
12208 ^cun/*cun$
8207 ^prus/*prus$
5205 ^o/*o$
4218 ^comente/*comente$
4100 ^fintzas/*fintzas$
3068 ^pustis/*pustis$
2658 ^annos/*annos$
2623 ^totu/*totu$
2589 ^ma/*ma$
2417 ^sua/*sua$
2376 ^parte/*parte$
2336 ^po/*po$
2250 ^Sardigna/*Sardigna$
2233 ^intre/*intre$
2120 ^ca/*ca$
2070 ^tzitade/*tzitade$
1964 ^che/*che$
1888 ^ue/*ue$
1873 ^bidda/*bidda$
1739 ^manera/*manera$
coverage: 963208 / 1863589 (~0.51685645279082458632)

** The number of words in the <code>large</code> corpus: ~1.85M words
** The number of stems in the transducer: ~85.5k stems

* For MT in the direction we developed (<code>srd-eng</code>):
** WER and PER over <code>longer</code> corpus:
-------------------------------------------------------
Number of words in reference: 315
Number of words in test: 341
Number of unknown words (marked with a star) in test: 35
Percentage of unknown words: 10.26 %

Results when removing unknown-word marks (stars)
-------------------------------------------------------
Edit distance: 246
Word error rate (WER): 78.10 %
Number of position-independent correct words: 118
Position-independent word error rate (PER): 70.79 %
** The proportion of stems translated correctly in the <code>longer</code> corpus.
118/341 = 34.6%
** Trimmed coverage over <code>longer</code> and <code>large</code> corpora.
** The number of tokens in <code>longer</code> and <code>large</code> corpora.
***<code>longer</code>: 341 tokens
***<code>large</code>: ~1.85M tokens

==10 sentences glosses and outputs==
*Note: '''These are outputs at end of lexical transfer before lexical selection and other weeks' improvements were implemented'''
{| cellpadding=5
|Sardinian sentence || intended English translation || output of srd-eng-biltrans (lexical transfer) mode || output of srd-eng (full translation) mode
|-
|1) Su sardu est una limba antica. || Sardinian is an ancient language. || ^Su<det><def><m><sg>/The<det><def><m><sg>$ ^sardu<n><m><sg>/Sardinian<n><sg>$ ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$ ^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$^.<sent>/.<sent>$^.<sent>/.<sent>$
|| #The Sardinian #be #a language #ancient
|-
|2) Pro bider s'artìculu sighire custu culligamentu. || To read the article click on this link. || ^Pro<pr>/For<pr>/To<pr>$ ^bider<vblex><inf>/read<vblex><inf>$ ^su<det><def><mf><sg>/the<det><def><mf><sg>$ ^artìculu<n><m><sg>/article<n><sg>$ ^sighire<vblex><inf>/click<vblex><inf>$ ^custu<det><dem><m><sg>/this<det><m><sg>$ ^culligamentu<n><m><sg>/link<n><sg>$^.<sent>/.<sent>$^.<sent>/.<sent>$<m><sg>$ ^culligamentu<n><m><sg>/link<n><sg>$^.<sent>/.<sent>$^.<sent>/.<sent>$
|| For read #the article click #this link.
|-
|3) Su trenu sinke fit andande. || The train was leaving. || ^Su<det><def><m><sg>/The<det><def><m><sg>$ ^trenu<n><m><sg>/train<n><sg>$ ^sinke<cnjadv>/$ ^èssere<vbser><pii><p3><sg>/be<vbser><pii><p3><sg>$ ^andare<vblex><ger>/leave<vblex><ger>/go<vblex><ger>$^.<sent>/.<sent>$^.<sent>/.<sent>$

|| #The train #be leaving.
|-
|4) Su trenu at a arrivare a sas deke. || The train will arrive at ten. || ^Su<det><def><m><sg>/The<det><def><m><sg>$ ^trenu<n><m><sg>/train<n><sg>$ ^àere<vbhaver><pri><p3><sg>/have<vbhaver><pri><p3><sg>$ ^a<pr>/at<pr>/on<pr>/to<pr>$ ^arrivare<vblex><inf>/arrive<vblex><inf>$ ^a<pr>/at<pr>/on<pr>/to<pr>$ ^su<det><def><f><pl>/the<det><def><f><pl>$ ^deke<num><mf><sp>/ten<num><mf><sp>$^.<sent>/.<sent>$^.<sent>/.<sent>$
|| #The train #have at arrive at #the #ten.
|-
|5) Su trenu devet arrivare a sas deke. || The train should arrive at ten. || ^Su<det><def><m><sg>/The<det><def><m><sg>$ ^trenu<n><m><sg>/train<n><sg>$ ^dèvere<vblex><pri><p3><sg>/shall<vbmod><pri><p3><sg>$ ^arrivare<vblex><inf>/arrive<vblex><inf>$ ^a<pr>/at<pr>/on<pr>/to<pr>$ ^su<det><def><f><pl>/the<det><def><f><pl>$ ^deke<num><mf><sp>/ten<num><mf><sp>$^.<sent>/.<sent>$^.<sent>/.<sent>$
|| #The train #shall arrive at #the #ten.
|-
|6) T'appo natu ki su trenu devíat arrivare a sas deke. || I told you that the train would arrive at ten. || ^Ti<prn><pro><p2><mf><sg>/You<prn><pro><p2><mf><sg>$ ^àere<vbhaver><pri><p1><sg>/have<vbhaver><pri><p1><sg>$ ^nàrrere<vblex><pp><m><sg>/tell<vblex><pp><m><sg>$ ^chi<cnjsub>/that<cnjsub>$ ^su<det><def><m><sg>/the<det><def><m><sg>$ ^trenu<n><m><sg>/train<n><sg>$ ^dèvere<vblex><pii><p3><sg>/shall<vbmod><pii><p3><sg>$ ^arrivare<vblex><inf>/arrive<vblex><inf>$ ^a<pr>/at<pr>/on<pr>/to<pr>$ ^su<det><def><f><pl>/the<det><def><f><pl>$ ^deke<num><mf><sp>/ten<num><mf><sp>$^.<sent>/.<sent>$^.<sent>/.<sent>$
|| #You #have #tell that #the train #shall arrive at #the #ten.
|-
|7) No'isco si at a pròere cras. || I do not know if it will rain tomorrow. || ^No<adv>/Not<adv>$'^iscoare<vblex><pri><p1><sg>/know<vblex><pri><p1><sg>$ ^si<cnjsub>/if<cnjsub>$ ^àere<vbhaver><pri><p3><sg>/have<vbhaver><pri><p3><sg>$ ^a<pr>/at<pr>/on<pr>/to<pr>$ ^pròere<vblex><inf>/rain<vblex><inf>$ ^cras<adv>/tomorrow<adv>$^.<sent>/.<sent>$
|| Not'#know if #have at rain tomorrow

|-
|8) Una de sas berbekes est maláida. || One of the sheep is sick. || ^Unu<num><f><sp>/One<num><f><sp>$ ^de<pr>/to<pr>/of<pr>$ ^su<det><def><f><pl>/the<det><def><f><pl>$ ^berbeke<n><f><pl>/sheep<n><pl>$ ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$ ^malàidu<adj><f><sg>/sick<adj><f><sg>$^.<sent>/.<sent>$
|| #One to #the sheep #be #sick

|-
|9) Appo pèrditu duos de sos libros meos. || I have lost two of my books. || ^Àere<vbhaver><pri><p1><sg>/Have<vbhaver><pri><p1><sg>$ ^pèrdere<vblex><pp><m><sg>/lose<vblex><pp><m><sg>$ ^duos<num><m><sp>/two<num><m><sp>$ ^de<pr>/to<pr>/of<pr>$ ^su<det><def><m><pl>/the<det><def><m><pl>$ ^libru<n><m><pl>/book<n><pl>$ ^meu<prn><pos><m><pl>/my<prn><pos><m><pl>$^.<sent>/.<sent>$

|| #Have #lose #two to #the books #my

|-
|10) M'an natu ki su trenu devíat arrivare a sas nove. || They told me that the train was supposed to arrive at nine. || ^Mi<prn><pro><p1><mf><sg>/I<prn><pro><p1><mf><sg>$ ^àere<vbhaver><pri><p3><pl>/have<vbhaver><pri><p3><pl>$ ^nàrrere<vblex><pp><m><sg>/tell<vblex><pp><m><sg>$ ^chi<cnjsub>/that<cnjsub>$ ^su<det><def><m><sg>/the<det><def><m><sg>$ ^trenu<n><m><sg>/train<n><sg>$ ^dèvere<vblex><pii><p3><sg>/shall<vbmod><pii><p3><sg>$ ^arrivare<vblex><inf>/arrive<vblex><inf>$ ^a<pr>/at<pr>/on<pr>/to<pr>$ ^su<det><def><f><pl>/the<det><def><f><pl>$ ^nove<num><mf><sp>/nine<num><mf><sp>$^.<sent>/.<sent>$
|| #I #have #tell that #the train #shall arrive at #the #nine
|
|}

==expanding lexicon==

{| cellpadding=5
|medas || many || <adj>
|-https://wikis.swarthmore.edu/ling073/index.php?title=Sardinian_and_English&action=edit
|piseddas || girls || <n><pl>
|-
|sun || they are || <v>
|-
|bennidas || to come (home) || <v><pp><fpl>
|-
|balladu || to dance || <v><pp>
|-
|cantaiat || to sing || <v><sg3>
|-
|sos/sa || the || <det>
|-
|piattos || plates || <n><pl>
|-
|mesa || table || <n><sg>
|-
|bi/b' || N/A || <cl>
|-
|problemas || problems || <n><pl>
|-
|unu || one/a || <adj>/<det>
|-
|ube || where || <adv>
|-
|mortu || dead || <v><pp>
|-
|sordatos || soldiers || <n><pl>
|-
|tenimus || we have || <v><pl1>
|-
|frores || flowers || <n><pl>
|-
|keret || to be necessary || <v><sg3>
|-
|mancat || to be missing || <v><sg3>
|-
|ovos || eggs || <n><pl>
|-
|danca || meadow || <n>
|-
|ortu || orchard || <n>
|-
|frade || brother || <n>
|-
|fizza || daughter || <n>
|-
|re || king || <n>
|-
|ora || hour || <n>
|-
|subra || above/on || <prep>
|-
|a || to/at || <prep>
|-
|cumintzos || origins || <n><pl>
|-
|e || and || <conj>
|-
|andamentu || evolution || <n>
|-
|istòricu || historical || <adj>
|-
|de || of/to || <prep>
|-
|sa || the || <det>
|-
|poesia || poetry || <n>
|-
|a bolu || improvised || <adj> (a bolu = improvised, on the fly)
|-
|in || in || <prep>
|-
|sardu || Sardinian || <n>
|-
|logudoresu || Logudorese || <adj>
|-
|non || not || <adv>
|-
|ischit || known || <v><pp>
|-
|meda || much || <adv>
|-
|custu || this || <det><prox>
|-
|artìculu || article || <n>
|-
|chircat || tries || <v><sg3>
|-
|bogare || to bring out || <v>
|-
|pizu || surface || <n> (bogare a pizu = to shed light on, to bring to the surface; see complicated translations of bogare: [http://vocabolariocasu.isresardegna.it/index.php?key=b&int=0&lemmi=cerca&codice=b1264000 here])
|-
|ammentos || memories || <n><pl>
|-
|ammentu || memory || <n>
|-
|ammentare || to remember || <v>
|-
|documentados || documented || <adj>
|-
|si || [null] || <> -- reflexive
|-
|primas || first || <adj>
|-
|disputas || competitions || <n><pl>
|-
|primas || first || <adj>
|-
|tra || between || <prep>
|-
|poetes || poets || <n><pl>
|-
|cale || which || <prn><rel>
|-
|esserent || were || <v> past imperfect 3rd person plural
|-
|règulas || rules, modalities || <n><pl>
|-
|su || the || <det>
|-
|cunfruntu || confrontation || <n>
|-
|sende || being || <v><ger>
|-
|una || a/one || <art>/<adj>
|-
|chirca || research || <n>
|-
|andera || ongoing/progressive || <adj>
|-
|testu || text || <n>
|-
|diat || [null] || <subj><sg3>
|-
|poder || to be able to || <v><inf>
|-
|aer || to have || <v><inf> (also hàere or àere)
|-
|mudonzos || modifications || <n><pl>
|-
|mudonzos || modifications || <n><pl>
|-
|novas || new || <adj><pl>
|-
|noas || data || <n><pl>
|-
|Pro || to || <prep> <-- keep this in mind for lexical selection (to)
|-
|bider || to read || <v><inf>
|-
|artìculu || article || <n>
|-
|sighire || click on || <v><inf>
|-
|intrare || enter || <v><inf>
|-
|desizadu || desired || <adj>
|-
|trenu || train || <n>
|-
|sinke || [null] || <foc>
|-
|fit || was || <v><imp><sg3>
|-
|andande || leaving || <v><ger>
|-
|at || it will || <>
|-
|sas || the || <det>
|-
|deke || ten || <n>
|-
|devet || should || <adv>
|-
|deke || ten || <adj>
|-
|appo || I have || <v><sg1>
|-
|natu || told || <v><pp>
|-
|próere || to rain || <v><inf>
|-
|arrivare || to arrive || <v><inf>
|-
|isco || I know || <v><sg1>
|-
|si || if || <conj>
|-
|ki || that || <conj>
|-
|cras || tomorrow || <adv>
|-
|meos || my || <pos>
|-
|andatos || gone || <adj><pl>
|
|}

===glosses===

Cando so arrivatu a s'istazione, su trenu sink'andaiat

'when I arrived at the station, the train was leaving'

Su trenu sinke fit andande

'The train was leaving"

Su trenu at a arrivare a sas deke

'The train will arrive at ten o'clock'

Su trenu devet arrivare a sas deke

'The train is supposed to arrive at ten o'clock'

T'appo natu ki su trenu diat arrivare a sas deke

'I told you that the train would arrive at ten o'clock'

M'an natu ki su trenu devíat arrivare a sas nove

'They told me that the train was supposed to arrive at nine'

At a próere cras

'It will rain tomorrow'

Devet próere cras

'it is supposed to rain tomorrow'

At a próere cras? Si emmo abbarramus in domo, ma su nono andamus a mare

'Will it rain tomorrow? If so we shall stay at homr, buy if not we will go to the sea'

No'isco si at a próere cras

'I do to know whether it will rain tomorrow'

Una de sas berbekes est maláida

'one of the sheep is sick'

Appo pèrditu duos de sos libros meos

'I have lost two of my books'

Metas de custas pitzinnas sun galanas

'Many of these girls are pretty'

Una pitzinna meta bella

'a very beautiful girl'

Cussas duas bravas pitzinnas

'those two good girls'

unu better cane bellu

'a huge beautiful dog'

un'átteru bette cane

'another huge dog'

Sun andatos a Frantza

'they went to France'

Est ghiratu dae Corsica

'He returned from Corsica'

Connnosco bene sa Frantza

"i know France well'

Custu libru est iscrittu in tedescu

'This book is written in German'

Cussus paráula venit dae su catalanu

'This word comes from Catalan'

Su sardu est una limba antica

'Sardinian is an ancient language'

Appo mandicatu casu

'I ate cheese'

Laura est toddende frores

'Laura is picking flowers'

De frores non nd'appo tódditu

'I did not pick any flowers'

No'amus comporatu pane

'We did not buy bread'

Mandico sa pasta kin casu

'I ate pasta with cheese'

Tres sórrikes an mandicatu tottu su casu

'Three mice ate all the cheese'

semus ponnende vinu in ampullas

'We are putting wine in bottles'

lettu meu esr

'It is my bed'

No'appo lessu libru perunu

'i did not read any book'

Sos k'an furatu si dinari at a èssere punitos

'The people who stole the money will be punished'

Appo invitat sos de Juanne

'I invited Jon's family'

Cussa pinna est sa mea

'That pen is mine'

Cudda mákkina est sa de Juanne

'That car is John's'

Custa ricca at datu mili francos a su vetzu

'This rich woman gave a thousand lira to the old man'

Su guvernu devíat dare ua pensione a dondzi vetzu

'The government should give a pension to every old person'

==External Resources==

*Github repository for [https://github.com/apertium/apertium-srd Sardinian transducer] (and our [https://github.swarthmore.edu/Ling073-sp23/ling073-srd clone])
*Github repository for [https://github.com/apertium/apertium-eng English transducer]
*[https://www.limbasardasudsardigna.it/sar/images/Documenti/Didatica_e_Ainas/Ditzion%C3%A0riu%20Universale%20Rubattu.pdf Dictionary pdf]
*[http://ditzionariu.sardegnacultura.it/it/ Online official dictionary]
*[https://it.glosbe.com/sc/it Web-based machine translator]
*[http://vocabolariocasu.isresardegna.it/index.php?key=a&int=0&lemmi=cerca Sardinian-Italian web-based dictionary]
*[http://www.sardegnadigitallibrary.it/mmt/fullsize/2009050512495700047.pdf 1931 pdf with select translations]
*[https://onlinelibrary.wiley.com/doi/epdf/10.1111/j.0079-1636.2004.00130.x Definiteness effects: evidence from Sardinian]
*[https://www.icongrouponline.com/en/Detail/dictionary/049783698X/Webster%27s+Sardinian+-+English+Thesaurus+Dictionary: Webster's Sardinian English Thesaurus Dictionary]
*[https://www.academia.edu/15320922/Dizionario_della_lingua_Sarda_Vol_2 Italian-Sardinian Dictionary]
*[https://archive.org/details/vocabolariosardo00spanuoft/page/n361/mode/2up Old but extensive Sardo-Italian and vice versa dictionary]
*[https://limbasardasudsardigna.it/sar/images/Documenti/Didatica_e_Ainas/Vocabolariu_Sardu_Italianu_Spano.pdf nice Sardo-Italiano dictionary pdf]
*[http://www.fontesarda.it/sr/sr0045.htm Conjugations of "to have" in Sardinian]
*[https://sinnainotizie.com/2015/03/07/lezioni-di-grammatica-sardo-campidanese-undicesima-lezione-su-verbu-ai-aere/ Whole Sardinian grammar page about conjugations of to have all written in Sardinian language!]
*Sardinian grammar:[https://www.limbasardasudsardigna.it/sar/images/Documenti/Didatica_e_Ainas/grammatiga_sardo%20campidanese%20A.LEPORI.pdf pdf]
[[Category:Sp23_TranslationPairs]],[[Category:Sardinian]],[[Category:English]]

Sardinian and English

2023-05-05T19:18:24Z

Rorlija1: /* Final evaluation */

=Resources for Machine Translation from Sardinian to English=

==Developed Resources==
*[https://github.swarthmore.edu/Ling073-sp23/ling073-srd-eng-corpus Parallel corpus git repo].
*:Lines 1-8 from [http://maxia-mail.doomby.com/ this website].
*[https://github.swarthmore.edu/Ling073-sp23/ling073-srd-eng Git repo for language pair]
*[https://github.swarthmore.edu/Ling073-sp23/ling073-srd Git repo for Sardinian]
*[https://github.com/apertium/apertium-eng Forked git repo for English]
*[https://wikis.swarthmore.edu/ling073/Sardinian_and_English/Lexical_selection#srd_.E2.86.92_eng Lexical selection wiki]
*[https://wikis.swarthmore.edu/ling073/Sardinian_and_English/Contrastive_Grammar#Differences_in_parse_and_corresponding_examples Contrastive grammar wiki]
*[https://wikis.swarthmore.edu/ling073/Sardinian_and_English/Structural_transfer Structural transfer wiki]

==srd → eng evaluation==
*coverage of monolingual Sardinian transducer on srd.sentences.txt:
Number of tokenised words in the corpus: 262
Coverage: 94.66%
*coverage of bilingual transducer on srd.sentences
Number of tokenised words in the corpus: 266
Coverage: 85.71%

==Additions for polished RBMT system==
*Over 100 new stems to bilingual dictionary
*:(now we have 172 total entries in the .dix file)
*4 sets of lexical selection rules
*:(now we have rules that solve 5 problems in total)
*3 items from contrastive grammar implemented in transfer rules
*:(now we have rules that implement 4 total items)

==Final evaluation==
* For the monolingual transducer:
** Updated precision and recall against the (updated) <code>eval.test</code> and <code>eval.gold</code> files
** Coverage over the <code>large</code> corpus:
***90.4% with monolingual transducer: (mostly simple words that could easily be added)

TOP UNKNOWN WORDS:
2336 ^po/*po$
1275 ^che/*che$
448 ^i/*i$
387 ^norte/*norte$
377 ^The/*The$
353 ^of/*of$
297 ^poi/*poi$
269 ^del/*del$
241 ^the/*the$
235 ^da/*da$
215 ^ch/*ch$
211 ^Il/*Il$
205 ^chentza/*chentza$
200 ^br/*br$
199 ^Arbaree/*Arbaree$
197 ^della/*della$
192 ^stètiu/*stètiu$
165 ^ddoi/*ddoi$
154 ^B/*B$
145 ^Norte/*Norte$
coverage: 1648134 / 1822907 (~0.90412401729764601266)

***52% for bilingual transducer: (also mostly simple words that could easily be added)

TOP UNKNOWN WORDS:
12208 ^cun/*cun$
8207 ^prus/*prus$
5205 ^o/*o$
4218 ^comente/*comente$
4100 ^fintzas/*fintzas$
3068 ^pustis/*pustis$
2658 ^annos/*annos$
2623 ^totu/*totu$
2589 ^ma/*ma$
2417 ^sua/*sua$
2376 ^parte/*parte$
2336 ^po/*po$
2250 ^Sardigna/*Sardigna$
2233 ^intre/*intre$
2120 ^ca/*ca$
2070 ^tzitade/*tzitade$
1964 ^che/*che$
1888 ^ue/*ue$
1873 ^bidda/*bidda$
1739 ^manera/*manera$
coverage: 963208 / 1863589 (~0.51685645279082458632)

** The number of words in the <code>large</code> corpus: ~1.85M words
** The number of stems in the transducer: ~85.5k stems

* For MT in the direction we developed (<code>srd-eng</code>):
** WER and PER over <code>longer</code> corpus:
-------------------------------------------------------
Number of words in reference: 315
Number of words in test: 341
Number of unknown words (marked with a star) in test: 35
Percentage of unknown words: 10.26 %

Results when removing unknown-word marks (stars)
-------------------------------------------------------
Edit distance: 246
Word error rate (WER): 78.10 %
Number of position-independent correct words: 118
Position-independent word error rate (PER): 70.79 %
** The proportion of stems translated correctly in the <code>longer</code> corpus.
118/341 = 34.6%
** Trimmed coverage over <code>longer</code> and <code>large</code> corpora.
** The number of tokens in <code>longer</code> and <code>large</code> corpora.
***<code>longer</code>: 341 tokens
***<code>large</code>: xxx tokens

==10 sentences glosses and outputs==
*Note: '''These are outputs at end of lexical transfer before lexical selection and other weeks' improvements were implemented'''
{| cellpadding=5
|Sardinian sentence || intended English translation || output of srd-eng-biltrans (lexical transfer) mode || output of srd-eng (full translation) mode
|-
|1) Su sardu est una limba antica. || Sardinian is an ancient language. || ^Su<det><def><m><sg>/The<det><def><m><sg>$ ^sardu<n><m><sg>/Sardinian<n><sg>$ ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$ ^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$^.<sent>/.<sent>$^.<sent>/.<sent>$
|| #The Sardinian #be #a language #ancient
|-
|2) Pro bider s'artìculu sighire custu culligamentu. || To read the article click on this link. || ^Pro<pr>/For<pr>/To<pr>$ ^bider<vblex><inf>/read<vblex><inf>$ ^su<det><def><mf><sg>/the<det><def><mf><sg>$ ^artìculu<n><m><sg>/article<n><sg>$ ^sighire<vblex><inf>/click<vblex><inf>$ ^custu<det><dem><m><sg>/this<det><m><sg>$ ^culligamentu<n><m><sg>/link<n><sg>$^.<sent>/.<sent>$^.<sent>/.<sent>$<m><sg>$ ^culligamentu<n><m><sg>/link<n><sg>$^.<sent>/.<sent>$^.<sent>/.<sent>$
|| For read #the article click #this link.
|-
|3) Su trenu sinke fit andande. || The train was leaving. || ^Su<det><def><m><sg>/The<det><def><m><sg>$ ^trenu<n><m><sg>/train<n><sg>$ ^sinke<cnjadv>/$ ^èssere<vbser><pii><p3><sg>/be<vbser><pii><p3><sg>$ ^andare<vblex><ger>/leave<vblex><ger>/go<vblex><ger>$^.<sent>/.<sent>$^.<sent>/.<sent>$

|| #The train #be leaving.
|-
|4) Su trenu at a arrivare a sas deke. || The train will arrive at ten. || ^Su<det><def><m><sg>/The<det><def><m><sg>$ ^trenu<n><m><sg>/train<n><sg>$ ^àere<vbhaver><pri><p3><sg>/have<vbhaver><pri><p3><sg>$ ^a<pr>/at<pr>/on<pr>/to<pr>$ ^arrivare<vblex><inf>/arrive<vblex><inf>$ ^a<pr>/at<pr>/on<pr>/to<pr>$ ^su<det><def><f><pl>/the<det><def><f><pl>$ ^deke<num><mf><sp>/ten<num><mf><sp>$^.<sent>/.<sent>$^.<sent>/.<sent>$
|| #The train #have at arrive at #the #ten.
|-
|5) Su trenu devet arrivare a sas deke. || The train should arrive at ten. || ^Su<det><def><m><sg>/The<det><def><m><sg>$ ^trenu<n><m><sg>/train<n><sg>$ ^dèvere<vblex><pri><p3><sg>/shall<vbmod><pri><p3><sg>$ ^arrivare<vblex><inf>/arrive<vblex><inf>$ ^a<pr>/at<pr>/on<pr>/to<pr>$ ^su<det><def><f><pl>/the<det><def><f><pl>$ ^deke<num><mf><sp>/ten<num><mf><sp>$^.<sent>/.<sent>$^.<sent>/.<sent>$
|| #The train #shall arrive at #the #ten.
|-
|6) T'appo natu ki su trenu devíat arrivare a sas deke. || I told you that the train would arrive at ten. || ^Ti<prn><pro><p2><mf><sg>/You<prn><pro><p2><mf><sg>$ ^àere<vbhaver><pri><p1><sg>/have<vbhaver><pri><p1><sg>$ ^nàrrere<vblex><pp><m><sg>/tell<vblex><pp><m><sg>$ ^chi<cnjsub>/that<cnjsub>$ ^su<det><def><m><sg>/the<det><def><m><sg>$ ^trenu<n><m><sg>/train<n><sg>$ ^dèvere<vblex><pii><p3><sg>/shall<vbmod><pii><p3><sg>$ ^arrivare<vblex><inf>/arrive<vblex><inf>$ ^a<pr>/at<pr>/on<pr>/to<pr>$ ^su<det><def><f><pl>/the<det><def><f><pl>$ ^deke<num><mf><sp>/ten<num><mf><sp>$^.<sent>/.<sent>$^.<sent>/.<sent>$
|| #You #have #tell that #the train #shall arrive at #the #ten.
|-
|7) No'isco si at a pròere cras. || I do not know if it will rain tomorrow. || ^No<adv>/Not<adv>$'^iscoare<vblex><pri><p1><sg>/know<vblex><pri><p1><sg>$ ^si<cnjsub>/if<cnjsub>$ ^àere<vbhaver><pri><p3><sg>/have<vbhaver><pri><p3><sg>$ ^a<pr>/at<pr>/on<pr>/to<pr>$ ^pròere<vblex><inf>/rain<vblex><inf>$ ^cras<adv>/tomorrow<adv>$^.<sent>/.<sent>$
|| Not'#know if #have at rain tomorrow

|-
|8) Una de sas berbekes est maláida. || One of the sheep is sick. || ^Unu<num><f><sp>/One<num><f><sp>$ ^de<pr>/to<pr>/of<pr>$ ^su<det><def><f><pl>/the<det><def><f><pl>$ ^berbeke<n><f><pl>/sheep<n><pl>$ ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$ ^malàidu<adj><f><sg>/sick<adj><f><sg>$^.<sent>/.<sent>$
|| #One to #the sheep #be #sick

|-
|9) Appo pèrditu duos de sos libros meos. || I have lost two of my books. || ^Àere<vbhaver><pri><p1><sg>/Have<vbhaver><pri><p1><sg>$ ^pèrdere<vblex><pp><m><sg>/lose<vblex><pp><m><sg>$ ^duos<num><m><sp>/two<num><m><sp>$ ^de<pr>/to<pr>/of<pr>$ ^su<det><def><m><pl>/the<det><def><m><pl>$ ^libru<n><m><pl>/book<n><pl>$ ^meu<prn><pos><m><pl>/my<prn><pos><m><pl>$^.<sent>/.<sent>$

|| #Have #lose #two to #the books #my

|-
|10) M'an natu ki su trenu devíat arrivare a sas nove. || They told me that the train was supposed to arrive at nine. || ^Mi<prn><pro><p1><mf><sg>/I<prn><pro><p1><mf><sg>$ ^àere<vbhaver><pri><p3><pl>/have<vbhaver><pri><p3><pl>$ ^nàrrere<vblex><pp><m><sg>/tell<vblex><pp><m><sg>$ ^chi<cnjsub>/that<cnjsub>$ ^su<det><def><m><sg>/the<det><def><m><sg>$ ^trenu<n><m><sg>/train<n><sg>$ ^dèvere<vblex><pii><p3><sg>/shall<vbmod><pii><p3><sg>$ ^arrivare<vblex><inf>/arrive<vblex><inf>$ ^a<pr>/at<pr>/on<pr>/to<pr>$ ^su<det><def><f><pl>/the<det><def><f><pl>$ ^nove<num><mf><sp>/nine<num><mf><sp>$^.<sent>/.<sent>$
|| #I #have #tell that #the train #shall arrive at #the #nine
|
|}

==expanding lexicon==

{| cellpadding=5
|medas || many || <adj>
|-https://wikis.swarthmore.edu/ling073/index.php?title=Sardinian_and_English&action=edit
|piseddas || girls || <n><pl>
|-
|sun || they are || <v>
|-
|bennidas || to come (home) || <v><pp><fpl>
|-
|balladu || to dance || <v><pp>
|-
|cantaiat || to sing || <v><sg3>
|-
|sos/sa || the || <det>
|-
|piattos || plates || <n><pl>
|-
|mesa || table || <n><sg>
|-
|bi/b' || N/A || <cl>
|-
|problemas || problems || <n><pl>
|-
|unu || one/a || <adj>/<det>
|-
|ube || where || <adv>
|-
|mortu || dead || <v><pp>
|-
|sordatos || soldiers || <n><pl>
|-
|tenimus || we have || <v><pl1>
|-
|frores || flowers || <n><pl>
|-
|keret || to be necessary || <v><sg3>
|-
|mancat || to be missing || <v><sg3>
|-
|ovos || eggs || <n><pl>
|-
|danca || meadow || <n>
|-
|ortu || orchard || <n>
|-
|frade || brother || <n>
|-
|fizza || daughter || <n>
|-
|re || king || <n>
|-
|ora || hour || <n>
|-
|subra || above/on || <prep>
|-
|a || to/at || <prep>
|-
|cumintzos || origins || <n><pl>
|-
|e || and || <conj>
|-
|andamentu || evolution || <n>
|-
|istòricu || historical || <adj>
|-
|de || of/to || <prep>
|-
|sa || the || <det>
|-
|poesia || poetry || <n>
|-
|a bolu || improvised || <adj> (a bolu = improvised, on the fly)
|-
|in || in || <prep>
|-
|sardu || Sardinian || <n>
|-
|logudoresu || Logudorese || <adj>
|-
|non || not || <adv>
|-
|ischit || known || <v><pp>
|-
|meda || much || <adv>
|-
|custu || this || <det><prox>
|-
|artìculu || article || <n>
|-
|chircat || tries || <v><sg3>
|-
|bogare || to bring out || <v>
|-
|pizu || surface || <n> (bogare a pizu = to shed light on, to bring to the surface; see complicated translations of bogare: [http://vocabolariocasu.isresardegna.it/index.php?key=b&int=0&lemmi=cerca&codice=b1264000 here])
|-
|ammentos || memories || <n><pl>
|-
|ammentu || memory || <n>
|-
|ammentare || to remember || <v>
|-
|documentados || documented || <adj>
|-
|si || [null] || <> -- reflexive
|-
|primas || first || <adj>
|-
|disputas || competitions || <n><pl>
|-
|primas || first || <adj>
|-
|tra || between || <prep>
|-
|poetes || poets || <n><pl>
|-
|cale || which || <prn><rel>
|-
|esserent || were || <v> past imperfect 3rd person plural
|-
|règulas || rules, modalities || <n><pl>
|-
|su || the || <det>
|-
|cunfruntu || confrontation || <n>
|-
|sende || being || <v><ger>
|-
|una || a/one || <art>/<adj>
|-
|chirca || research || <n>
|-
|andera || ongoing/progressive || <adj>
|-
|testu || text || <n>
|-
|diat || [null] || <subj><sg3>
|-
|poder || to be able to || <v><inf>
|-
|aer || to have || <v><inf> (also hàere or àere)
|-
|mudonzos || modifications || <n><pl>
|-
|mudonzos || modifications || <n><pl>
|-
|novas || new || <adj><pl>
|-
|noas || data || <n><pl>
|-
|Pro || to || <prep> <-- keep this in mind for lexical selection (to)
|-
|bider || to read || <v><inf>
|-
|artìculu || article || <n>
|-
|sighire || click on || <v><inf>
|-
|intrare || enter || <v><inf>
|-
|desizadu || desired || <adj>
|-
|trenu || train || <n>
|-
|sinke || [null] || <foc>
|-
|fit || was || <v><imp><sg3>
|-
|andande || leaving || <v><ger>
|-
|at || it will || <>
|-
|sas || the || <det>
|-
|deke || ten || <n>
|-
|devet || should || <adv>
|-
|deke || ten || <adj>
|-
|appo || I have || <v><sg1>
|-
|natu || told || <v><pp>
|-
|próere || to rain || <v><inf>
|-
|arrivare || to arrive || <v><inf>
|-
|isco || I know || <v><sg1>
|-
|si || if || <conj>
|-
|ki || that || <conj>
|-
|cras || tomorrow || <adv>
|-
|meos || my || <pos>
|-
|andatos || gone || <adj><pl>
|
|}

===glosses===

Cando so arrivatu a s'istazione, su trenu sink'andaiat

'when I arrived at the station, the train was leaving'

Su trenu sinke fit andande

'The train was leaving"

Su trenu at a arrivare a sas deke

'The train will arrive at ten o'clock'

Su trenu devet arrivare a sas deke

'The train is supposed to arrive at ten o'clock'

T'appo natu ki su trenu diat arrivare a sas deke

'I told you that the train would arrive at ten o'clock'

M'an natu ki su trenu devíat arrivare a sas nove

'They told me that the train was supposed to arrive at nine'

At a próere cras

'It will rain tomorrow'

Devet próere cras

'it is supposed to rain tomorrow'

At a próere cras? Si emmo abbarramus in domo, ma su nono andamus a mare

'Will it rain tomorrow? If so we shall stay at homr, buy if not we will go to the sea'

No'isco si at a próere cras

'I do to know whether it will rain tomorrow'

Una de sas berbekes est maláida

'one of the sheep is sick'

Appo pèrditu duos de sos libros meos

'I have lost two of my books'

Metas de custas pitzinnas sun galanas

'Many of these girls are pretty'

Una pitzinna meta bella

'a very beautiful girl'

Cussas duas bravas pitzinnas

'those two good girls'

unu better cane bellu

'a huge beautiful dog'

un'átteru bette cane

'another huge dog'

Sun andatos a Frantza

'they went to France'

Est ghiratu dae Corsica

'He returned from Corsica'

Connnosco bene sa Frantza

"i know France well'

Custu libru est iscrittu in tedescu

'This book is written in German'

Cussus paráula venit dae su catalanu

'This word comes from Catalan'

Su sardu est una limba antica

'Sardinian is an ancient language'

Appo mandicatu casu

'I ate cheese'

Laura est toddende frores

'Laura is picking flowers'

De frores non nd'appo tódditu

'I did not pick any flowers'

No'amus comporatu pane

'We did not buy bread'

Mandico sa pasta kin casu

'I ate pasta with cheese'

Tres sórrikes an mandicatu tottu su casu

'Three mice ate all the cheese'

semus ponnende vinu in ampullas

'We are putting wine in bottles'

lettu meu esr

'It is my bed'

No'appo lessu libru perunu

'i did not read any book'

Sos k'an furatu si dinari at a èssere punitos

'The people who stole the money will be punished'

Appo invitat sos de Juanne

'I invited Jon's family'

Cussa pinna est sa mea

'That pen is mine'

Cudda mákkina est sa de Juanne

'That car is John's'

Custa ricca at datu mili francos a su vetzu

'This rich woman gave a thousand lira to the old man'

Su guvernu devíat dare ua pensione a dondzi vetzu

'The government should give a pension to every old person'

==External Resources==

*Github repository for [https://github.com/apertium/apertium-srd Sardinian transducer] (and our [https://github.swarthmore.edu/Ling073-sp23/ling073-srd clone])
*Github repository for [https://github.com/apertium/apertium-eng English transducer]
*[https://www.limbasardasudsardigna.it/sar/images/Documenti/Didatica_e_Ainas/Ditzion%C3%A0riu%20Universale%20Rubattu.pdf Dictionary pdf]
*[http://ditzionariu.sardegnacultura.it/it/ Online official dictionary]
*[https://it.glosbe.com/sc/it Web-based machine translator]
*[http://vocabolariocasu.isresardegna.it/index.php?key=a&int=0&lemmi=cerca Sardinian-Italian web-based dictionary]
*[http://www.sardegnadigitallibrary.it/mmt/fullsize/2009050512495700047.pdf 1931 pdf with select translations]
*[https://onlinelibrary.wiley.com/doi/epdf/10.1111/j.0079-1636.2004.00130.x Definiteness effects: evidence from Sardinian]
*[https://www.icongrouponline.com/en/Detail/dictionary/049783698X/Webster%27s+Sardinian+-+English+Thesaurus+Dictionary: Webster's Sardinian English Thesaurus Dictionary]
*[https://www.academia.edu/15320922/Dizionario_della_lingua_Sarda_Vol_2 Italian-Sardinian Dictionary]
*[https://archive.org/details/vocabolariosardo00spanuoft/page/n361/mode/2up Old but extensive Sardo-Italian and vice versa dictionary]
*[https://limbasardasudsardigna.it/sar/images/Documenti/Didatica_e_Ainas/Vocabolariu_Sardu_Italianu_Spano.pdf nice Sardo-Italiano dictionary pdf]
*[http://www.fontesarda.it/sr/sr0045.htm Conjugations of "to have" in Sardinian]
*[https://sinnainotizie.com/2015/03/07/lezioni-di-grammatica-sardo-campidanese-undicesima-lezione-su-verbu-ai-aere/ Whole Sardinian grammar page about conjugations of to have all written in Sardinian language!]
*Sardinian grammar:[https://www.limbasardasudsardigna.it/sar/images/Documenti/Didatica_e_Ainas/grammatiga_sardo%20campidanese%20A.LEPORI.pdf pdf]
[[Category:Sp23_TranslationPairs]],[[Category:Sardinian]],[[Category:English]]

Sardinian and English

2023-05-05T19:16:30Z

Rorlija1: /* Final evaluation */

=Resources for Machine Translation from Sardinian to English=

==Developed Resources==
*[https://github.swarthmore.edu/Ling073-sp23/ling073-srd-eng-corpus Parallel corpus git repo].
*:Lines 1-8 from [http://maxia-mail.doomby.com/ this website].
*[https://github.swarthmore.edu/Ling073-sp23/ling073-srd-eng Git repo for language pair]
*[https://github.swarthmore.edu/Ling073-sp23/ling073-srd Git repo for Sardinian]
*[https://github.com/apertium/apertium-eng Forked git repo for English]
*[https://wikis.swarthmore.edu/ling073/Sardinian_and_English/Lexical_selection#srd_.E2.86.92_eng Lexical selection wiki]
*[https://wikis.swarthmore.edu/ling073/Sardinian_and_English/Contrastive_Grammar#Differences_in_parse_and_corresponding_examples Contrastive grammar wiki]
*[https://wikis.swarthmore.edu/ling073/Sardinian_and_English/Structural_transfer Structural transfer wiki]

==srd → eng evaluation==
*coverage of monolingual Sardinian transducer on srd.sentences.txt:
Number of tokenised words in the corpus: 262
Coverage: 94.66%
*coverage of bilingual transducer on srd.sentences
Number of tokenised words in the corpus: 266
Coverage: 85.71%

==Additions for polished RBMT system==
*Over 100 new stems to bilingual dictionary
*:(now we have 172 total entries in the .dix file)
*4 sets of lexical selection rules
*:(now we have rules that solve 5 problems in total)
*3 items from contrastive grammar implemented in transfer rules
*:(now we have rules that implement 4 total items)

==Final evaluation==
* For the monolingual transducer:
** Updated precision and recall against the (updated) <code>eval.test</code> and <code>eval.gold</code> files
** Coverage over the <code>large</code> corpus:
***90.4% with monolingual transducer
TOP UNKNOWN WORDS:
2336 ^po/*po$
1275 ^che/*che$
448 ^i/*i$
387 ^norte/*norte$
377 ^The/*The$
353 ^of/*of$
297 ^poi/*poi$
269 ^del/*del$
241 ^the/*the$
235 ^da/*da$
215 ^ch/*ch$
211 ^Il/*Il$
205 ^chentza/*chentza$
200 ^br/*br$
199 ^Arbaree/*Arbaree$
197 ^della/*della$
192 ^stètiu/*stètiu$
165 ^ddoi/*ddoi$
154 ^B/*B$
145 ^Norte/*Norte$
coverage: 1648134 / 1822907 (~0.90412401729764601266)

TOP UNKNOWN WORDS:
12208 ^cun/*cun$
8207 ^prus/*prus$
5205 ^o/*o$
4218 ^comente/*comente$
4100 ^fintzas/*fintzas$
3068 ^pustis/*pustis$
2658 ^annos/*annos$
2623 ^totu/*totu$
2589 ^ma/*ma$
2417 ^sua/*sua$
2376 ^parte/*parte$
2336 ^po/*po$
2250 ^Sardigna/*Sardigna$
2233 ^intre/*intre$
2120 ^ca/*ca$
2070 ^tzitade/*tzitade$
1964 ^che/*che$
1888 ^ue/*ue$
1873 ^bidda/*bidda$
1739 ^manera/*manera$
coverage: 963208 / 1863589 (~0.51685645279082458632)

** The number of words in the <code>large</code> corpus: ~1.85M words
** The number of stems in the transducer: ~85.5k stems

* For MT in the direction we developed (<code>srd-eng</code>):
** WER and PER over <code>longer</code> corpus:
-------------------------------------------------------
Number of words in reference: 315
Number of words in test: 341
Number of unknown words (marked with a star) in test: 35
Percentage of unknown words: 10.26 %

Results when removing unknown-word marks (stars)
-------------------------------------------------------
Edit distance: 246
Word error rate (WER): 78.10 %
Number of position-independent correct words: 118
Position-independent word error rate (PER): 70.79 %
** The proportion of stems translated correctly in the <code>longer</code> corpus.
118/341 = 34.6%
** Trimmed coverage over <code>longer</code> and <code>large</code> corpora.
** The number of tokens in <code>longer</code> and <code>large</code> corpora.
***<code>longer</code>: 341 tokens
***<code>large</code>: xxx tokens

==10 sentences glosses and outputs==
*Note: '''These are outputs at end of lexical transfer before lexical selection and other weeks' improvements were implemented'''
{| cellpadding=5
|Sardinian sentence || intended English translation || output of srd-eng-biltrans (lexical transfer) mode || output of srd-eng (full translation) mode
|-
|1) Su sardu est una limba antica. || Sardinian is an ancient language. || ^Su<det><def><m><sg>/The<det><def><m><sg>$ ^sardu<n><m><sg>/Sardinian<n><sg>$ ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$ ^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$^.<sent>/.<sent>$^.<sent>/.<sent>$
|| #The Sardinian #be #a language #ancient
|-
|2) Pro bider s'artìculu sighire custu culligamentu. || To read the article click on this link. || ^Pro<pr>/For<pr>/To<pr>$ ^bider<vblex><inf>/read<vblex><inf>$ ^su<det><def><mf><sg>/the<det><def><mf><sg>$ ^artìculu<n><m><sg>/article<n><sg>$ ^sighire<vblex><inf>/click<vblex><inf>$ ^custu<det><dem><m><sg>/this<det><m><sg>$ ^culligamentu<n><m><sg>/link<n><sg>$^.<sent>/.<sent>$^.<sent>/.<sent>$<m><sg>$ ^culligamentu<n><m><sg>/link<n><sg>$^.<sent>/.<sent>$^.<sent>/.<sent>$
|| For read #the article click #this link.
|-
|3) Su trenu sinke fit andande. || The train was leaving. || ^Su<det><def><m><sg>/The<det><def><m><sg>$ ^trenu<n><m><sg>/train<n><sg>$ ^sinke<cnjadv>/$ ^èssere<vbser><pii><p3><sg>/be<vbser><pii><p3><sg>$ ^andare<vblex><ger>/leave<vblex><ger>/go<vblex><ger>$^.<sent>/.<sent>$^.<sent>/.<sent>$

|| #The train #be leaving.
|-
|4) Su trenu at a arrivare a sas deke. || The train will arrive at ten. || ^Su<det><def><m><sg>/The<det><def><m><sg>$ ^trenu<n><m><sg>/train<n><sg>$ ^àere<vbhaver><pri><p3><sg>/have<vbhaver><pri><p3><sg>$ ^a<pr>/at<pr>/on<pr>/to<pr>$ ^arrivare<vblex><inf>/arrive<vblex><inf>$ ^a<pr>/at<pr>/on<pr>/to<pr>$ ^su<det><def><f><pl>/the<det><def><f><pl>$ ^deke<num><mf><sp>/ten<num><mf><sp>$^.<sent>/.<sent>$^.<sent>/.<sent>$
|| #The train #have at arrive at #the #ten.
|-
|5) Su trenu devet arrivare a sas deke. || The train should arrive at ten. || ^Su<det><def><m><sg>/The<det><def><m><sg>$ ^trenu<n><m><sg>/train<n><sg>$ ^dèvere<vblex><pri><p3><sg>/shall<vbmod><pri><p3><sg>$ ^arrivare<vblex><inf>/arrive<vblex><inf>$ ^a<pr>/at<pr>/on<pr>/to<pr>$ ^su<det><def><f><pl>/the<det><def><f><pl>$ ^deke<num><mf><sp>/ten<num><mf><sp>$^.<sent>/.<sent>$^.<sent>/.<sent>$
|| #The train #shall arrive at #the #ten.
|-
|6) T'appo natu ki su trenu devíat arrivare a sas deke. || I told you that the train would arrive at ten. || ^Ti<prn><pro><p2><mf><sg>/You<prn><pro><p2><mf><sg>$ ^àere<vbhaver><pri><p1><sg>/have<vbhaver><pri><p1><sg>$ ^nàrrere<vblex><pp><m><sg>/tell<vblex><pp><m><sg>$ ^chi<cnjsub>/that<cnjsub>$ ^su<det><def><m><sg>/the<det><def><m><sg>$ ^trenu<n><m><sg>/train<n><sg>$ ^dèvere<vblex><pii><p3><sg>/shall<vbmod><pii><p3><sg>$ ^arrivare<vblex><inf>/arrive<vblex><inf>$ ^a<pr>/at<pr>/on<pr>/to<pr>$ ^su<det><def><f><pl>/the<det><def><f><pl>$ ^deke<num><mf><sp>/ten<num><mf><sp>$^.<sent>/.<sent>$^.<sent>/.<sent>$
|| #You #have #tell that #the train #shall arrive at #the #ten.
|-
|7) No'isco si at a pròere cras. || I do not know if it will rain tomorrow. || ^No<adv>/Not<adv>$'^iscoare<vblex><pri><p1><sg>/know<vblex><pri><p1><sg>$ ^si<cnjsub>/if<cnjsub>$ ^àere<vbhaver><pri><p3><sg>/have<vbhaver><pri><p3><sg>$ ^a<pr>/at<pr>/on<pr>/to<pr>$ ^pròere<vblex><inf>/rain<vblex><inf>$ ^cras<adv>/tomorrow<adv>$^.<sent>/.<sent>$
|| Not'#know if #have at rain tomorrow

|-
|8) Una de sas berbekes est maláida. || One of the sheep is sick. || ^Unu<num><f><sp>/One<num><f><sp>$ ^de<pr>/to<pr>/of<pr>$ ^su<det><def><f><pl>/the<det><def><f><pl>$ ^berbeke<n><f><pl>/sheep<n><pl>$ ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$ ^malàidu<adj><f><sg>/sick<adj><f><sg>$^.<sent>/.<sent>$
|| #One to #the sheep #be #sick

|-
|9) Appo pèrditu duos de sos libros meos. || I have lost two of my books. || ^Àere<vbhaver><pri><p1><sg>/Have<vbhaver><pri><p1><sg>$ ^pèrdere<vblex><pp><m><sg>/lose<vblex><pp><m><sg>$ ^duos<num><m><sp>/two<num><m><sp>$ ^de<pr>/to<pr>/of<pr>$ ^su<det><def><m><pl>/the<det><def><m><pl>$ ^libru<n><m><pl>/book<n><pl>$ ^meu<prn><pos><m><pl>/my<prn><pos><m><pl>$^.<sent>/.<sent>$

|| #Have #lose #two to #the books #my

|-
|10) M'an natu ki su trenu devíat arrivare a sas nove. || They told me that the train was supposed to arrive at nine. || ^Mi<prn><pro><p1><mf><sg>/I<prn><pro><p1><mf><sg>$ ^àere<vbhaver><pri><p3><pl>/have<vbhaver><pri><p3><pl>$ ^nàrrere<vblex><pp><m><sg>/tell<vblex><pp><m><sg>$ ^chi<cnjsub>/that<cnjsub>$ ^su<det><def><m><sg>/the<det><def><m><sg>$ ^trenu<n><m><sg>/train<n><sg>$ ^dèvere<vblex><pii><p3><sg>/shall<vbmod><pii><p3><sg>$ ^arrivare<vblex><inf>/arrive<vblex><inf>$ ^a<pr>/at<pr>/on<pr>/to<pr>$ ^su<det><def><f><pl>/the<det><def><f><pl>$ ^nove<num><mf><sp>/nine<num><mf><sp>$^.<sent>/.<sent>$
|| #I #have #tell that #the train #shall arrive at #the #nine
|
|}

==expanding lexicon==

{| cellpadding=5
|medas || many || <adj>
|-https://wikis.swarthmore.edu/ling073/index.php?title=Sardinian_and_English&action=edit
|piseddas || girls || <n><pl>
|-
|sun || they are || <v>
|-
|bennidas || to come (home) || <v><pp><fpl>
|-
|balladu || to dance || <v><pp>
|-
|cantaiat || to sing || <v><sg3>
|-
|sos/sa || the || <det>
|-
|piattos || plates || <n><pl>
|-
|mesa || table || <n><sg>
|-
|bi/b' || N/A || <cl>
|-
|problemas || problems || <n><pl>
|-
|unu || one/a || <adj>/<det>
|-
|ube || where || <adv>
|-
|mortu || dead || <v><pp>
|-
|sordatos || soldiers || <n><pl>
|-
|tenimus || we have || <v><pl1>
|-
|frores || flowers || <n><pl>
|-
|keret || to be necessary || <v><sg3>
|-
|mancat || to be missing || <v><sg3>
|-
|ovos || eggs || <n><pl>
|-
|danca || meadow || <n>
|-
|ortu || orchard || <n>
|-
|frade || brother || <n>
|-
|fizza || daughter || <n>
|-
|re || king || <n>
|-
|ora || hour || <n>
|-
|subra || above/on || <prep>
|-
|a || to/at || <prep>
|-
|cumintzos || origins || <n><pl>
|-
|e || and || <conj>
|-
|andamentu || evolution || <n>
|-
|istòricu || historical || <adj>
|-
|de || of/to || <prep>
|-
|sa || the || <det>
|-
|poesia || poetry || <n>
|-
|a bolu || improvised || <adj> (a bolu = improvised, on the fly)
|-
|in || in || <prep>
|-
|sardu || Sardinian || <n>
|-
|logudoresu || Logudorese || <adj>
|-
|non || not || <adv>
|-
|ischit || known || <v><pp>
|-
|meda || much || <adv>
|-
|custu || this || <det><prox>
|-
|artìculu || article || <n>
|-
|chircat || tries || <v><sg3>
|-
|bogare || to bring out || <v>
|-
|pizu || surface || <n> (bogare a pizu = to shed light on, to bring to the surface; see complicated translations of bogare: [http://vocabolariocasu.isresardegna.it/index.php?key=b&int=0&lemmi=cerca&codice=b1264000 here])
|-
|ammentos || memories || <n><pl>
|-
|ammentu || memory || <n>
|-
|ammentare || to remember || <v>
|-
|documentados || documented || <adj>
|-
|si || [null] || <> -- reflexive
|-
|primas || first || <adj>
|-
|disputas || competitions || <n><pl>
|-
|primas || first || <adj>
|-
|tra || between || <prep>
|-
|poetes || poets || <n><pl>
|-
|cale || which || <prn><rel>
|-
|esserent || were || <v> past imperfect 3rd person plural
|-
|règulas || rules, modalities || <n><pl>
|-
|su || the || <det>
|-
|cunfruntu || confrontation || <n>
|-
|sende || being || <v><ger>
|-
|una || a/one || <art>/<adj>
|-
|chirca || research || <n>
|-
|andera || ongoing/progressive || <adj>
|-
|testu || text || <n>
|-
|diat || [null] || <subj><sg3>
|-
|poder || to be able to || <v><inf>
|-
|aer || to have || <v><inf> (also hàere or àere)
|-
|mudonzos || modifications || <n><pl>
|-
|mudonzos || modifications || <n><pl>
|-
|novas || new || <adj><pl>
|-
|noas || data || <n><pl>
|-
|Pro || to || <prep> <-- keep this in mind for lexical selection (to)
|-
|bider || to read || <v><inf>
|-
|artìculu || article || <n>
|-
|sighire || click on || <v><inf>
|-
|intrare || enter || <v><inf>
|-
|desizadu || desired || <adj>
|-
|trenu || train || <n>
|-
|sinke || [null] || <foc>
|-
|fit || was || <v><imp><sg3>
|-
|andande || leaving || <v><ger>
|-
|at || it will || <>
|-
|sas || the || <det>
|-
|deke || ten || <n>
|-
|devet || should || <adv>
|-
|deke || ten || <adj>
|-
|appo || I have || <v><sg1>
|-
|natu || told || <v><pp>
|-
|próere || to rain || <v><inf>
|-
|arrivare || to arrive || <v><inf>
|-
|isco || I know || <v><sg1>
|-
|si || if || <conj>
|-
|ki || that || <conj>
|-
|cras || tomorrow || <adv>
|-
|meos || my || <pos>
|-
|andatos || gone || <adj><pl>
|
|}

===glosses===

Cando so arrivatu a s'istazione, su trenu sink'andaiat

'when I arrived at the station, the train was leaving'

Su trenu sinke fit andande

'The train was leaving"

Su trenu at a arrivare a sas deke

'The train will arrive at ten o'clock'

Su trenu devet arrivare a sas deke

'The train is supposed to arrive at ten o'clock'

T'appo natu ki su trenu diat arrivare a sas deke

'I told you that the train would arrive at ten o'clock'

M'an natu ki su trenu devíat arrivare a sas nove

'They told me that the train was supposed to arrive at nine'

At a próere cras

'It will rain tomorrow'

Devet próere cras

'it is supposed to rain tomorrow'

At a próere cras? Si emmo abbarramus in domo, ma su nono andamus a mare

'Will it rain tomorrow? If so we shall stay at homr, buy if not we will go to the sea'

No'isco si at a próere cras

'I do to know whether it will rain tomorrow'

Una de sas berbekes est maláida

'one of the sheep is sick'

Appo pèrditu duos de sos libros meos

'I have lost two of my books'

Metas de custas pitzinnas sun galanas

'Many of these girls are pretty'

Una pitzinna meta bella

'a very beautiful girl'

Cussas duas bravas pitzinnas

'those two good girls'

unu better cane bellu

'a huge beautiful dog'

un'átteru bette cane

'another huge dog'

Sun andatos a Frantza

'they went to France'

Est ghiratu dae Corsica

'He returned from Corsica'

Connnosco bene sa Frantza

"i know France well'

Custu libru est iscrittu in tedescu

'This book is written in German'

Cussus paráula venit dae su catalanu

'This word comes from Catalan'

Su sardu est una limba antica

'Sardinian is an ancient language'

Appo mandicatu casu

'I ate cheese'

Laura est toddende frores

'Laura is picking flowers'

De frores non nd'appo tódditu

'I did not pick any flowers'

No'amus comporatu pane

'We did not buy bread'

Mandico sa pasta kin casu

'I ate pasta with cheese'

Tres sórrikes an mandicatu tottu su casu

'Three mice ate all the cheese'

semus ponnende vinu in ampullas

'We are putting wine in bottles'

lettu meu esr

'It is my bed'

No'appo lessu libru perunu

'i did not read any book'

Sos k'an furatu si dinari at a èssere punitos

'The people who stole the money will be punished'

Appo invitat sos de Juanne

'I invited Jon's family'

Cussa pinna est sa mea

'That pen is mine'

Cudda mákkina est sa de Juanne

'That car is John's'

Custa ricca at datu mili francos a su vetzu

'This rich woman gave a thousand lira to the old man'

Su guvernu devíat dare ua pensione a dondzi vetzu

'The government should give a pension to every old person'

==External Resources==

*Github repository for [https://github.com/apertium/apertium-srd Sardinian transducer] (and our [https://github.swarthmore.edu/Ling073-sp23/ling073-srd clone])
*Github repository for [https://github.com/apertium/apertium-eng English transducer]
*[https://www.limbasardasudsardigna.it/sar/images/Documenti/Didatica_e_Ainas/Ditzion%C3%A0riu%20Universale%20Rubattu.pdf Dictionary pdf]
*[http://ditzionariu.sardegnacultura.it/it/ Online official dictionary]
*[https://it.glosbe.com/sc/it Web-based machine translator]
*[http://vocabolariocasu.isresardegna.it/index.php?key=a&int=0&lemmi=cerca Sardinian-Italian web-based dictionary]
*[http://www.sardegnadigitallibrary.it/mmt/fullsize/2009050512495700047.pdf 1931 pdf with select translations]
*[https://onlinelibrary.wiley.com/doi/epdf/10.1111/j.0079-1636.2004.00130.x Definiteness effects: evidence from Sardinian]
*[https://www.icongrouponline.com/en/Detail/dictionary/049783698X/Webster%27s+Sardinian+-+English+Thesaurus+Dictionary: Webster's Sardinian English Thesaurus Dictionary]
*[https://www.academia.edu/15320922/Dizionario_della_lingua_Sarda_Vol_2 Italian-Sardinian Dictionary]
*[https://archive.org/details/vocabolariosardo00spanuoft/page/n361/mode/2up Old but extensive Sardo-Italian and vice versa dictionary]
*[https://limbasardasudsardigna.it/sar/images/Documenti/Didatica_e_Ainas/Vocabolariu_Sardu_Italianu_Spano.pdf nice Sardo-Italiano dictionary pdf]
*[http://www.fontesarda.it/sr/sr0045.htm Conjugations of "to have" in Sardinian]
*[https://sinnainotizie.com/2015/03/07/lezioni-di-grammatica-sardo-campidanese-undicesima-lezione-su-verbu-ai-aere/ Whole Sardinian grammar page about conjugations of to have all written in Sardinian language!]
*Sardinian grammar:[https://www.limbasardasudsardigna.it/sar/images/Documenti/Didatica_e_Ainas/grammatiga_sardo%20campidanese%20A.LEPORI.pdf pdf]
[[Category:Sp23_TranslationPairs]],[[Category:Sardinian]],[[Category:English]]

Wolof

2023-05-05T19:14:23Z

Rorlija1: /* Developed Resources */

Rowan Orlijan-Rhyne, Athena Basu, and Rhea Lim

Spring 2023
==Developed Resources==
======Keyboard Layout======
*See our [https://wikis.swarthmore.edu/ling073/Wolof/Keyboard Wolof Keyboard Wiki], where you will find a [https://github.swarthmore.edu/Ling073-sp23/ling073-wol-keyboard git repository] containing a Wolof keyboard layout.
======Morphology======
*See our [https://wikis.swarthmore.edu/ling073/Wolof/Grammar Wolof Grammar Wiki], where you will find documentation of Wolof grammar.
======Transducer======
*See our [https://wikis.swarthmore.edu/ling073/Wolof/Transducer Wolof Transducer Wiki], where you will find a [https://github.swarthmore.edu/Ling073-sp23/ling073-wol git repository] containing a Wolof morphological transducer.
*See also our [https://wikis.swarthmore.edu/ling073/Wolof/Disambiguator Wolof Disambiguator Wiki], where you will find notes about disambiguation implemented in our transducer.
======precisionRecall======
Totals: 102 forms, 146 tp, 144 fp, 0 tn, 18 fn
Precision: 50.34483%
Recall: 89.02439%

==External Resources==
======Computational resources (spell checkers, orthography converters, speech recognition software, keyboard layouts, machine translators):======
*Machine translator<ref>[https://jeloroc.wixsite.com/jangawoloftranslator English-Wolof Translator]</ref> - ©2023 Wolof Translations by Janga Wolof.
*Keyboard<ref>[https://www.lexilogos.com/keyboard/wolof.htm Wolof Keyboard]</ref> - Xavier Nègre © Lexilogos 2002-2021

======Dictionaries/phrasebooks/glossaries (multilingual and monolingual, online and paper):======
*Peace Corps resources<ref>[https://fsi-languages.yojik.eu/languages/PeaceCorps/Wolof/ Peace Corps Wolof Resource Collection]</ref> - unlisted, presumably public domain
*Peace Corps New Wolof Book<ref>[http://publish.illinois.edu/wolof201fall14/files/2014/08/NEW_WOLOF_BOOK.pdf Peace Corps New Wolof Book]</ref> - unlisted, presumably public domain
*A phrase guide<ref>[https://www.stcommunications.com/english-to-wolof-senegal-phrase-translation-guide/ STCommunications Phrase guide]</ref> - Copyright 2020 ® ST Communications
*Extensive online dictionary with some example sentences (English-Wolof)<ref>[https://jangawolof.org/dictionary-2/ Janga Wolof Dictionary]</ref> - all rights reserved
*1997 UCLA Eng-Wol dictionary<ref>[https://linguistics.ucla.edu/publications/opl_19.pdf UCLA Eng-Wol Dictionary]</ref> - copyright 1997 all rights reserved
*Resources for Wolof in Gambia<ref>[https://wolof.mofeko.com/#learn Mofeko]</ref> - all rights reserved
*Gan gi = The visitor : with a glossary of Wolof at the end of the book : a beginning self-study Wolof course for tourists and foreigners<ref>[Gan gi = The visitor : with a glossary of Wolof at the end of the book : a beginning self-study Wolof course for tourists and foreigners https://www.worldcat.org/title/841163586]</ref> - all rights reserved
*Wolof-French Dictionary<ref>[https://www.worldcat.org/title/39291762 Dictionnaire français-wolof]</ref> - all rights reserved
*Wolof-English phrasebook with audio<ref>[https://www.17-minute-world-languages.com/en/wolof/ 17 minute languages]</ref> - all rights reserved

======Grammatical descriptions (theoretical and pædagogical):======
*General overview of Wolof grammar<ref>[http://www.languagesgulper.com/eng/Wolof.html Languages Gulper Grammar]</ref>
*Long academic grammatical description<ref>[http://www.languagesgulper.com/eng/Wolof.html Wolof: A Grammatical Sketch]</ref>
*Noun classification resource<ref>[https://www.google.com/url?sa=t&rct=j&q=&esrc=s&source=web&cd=&ved=2ahUKEwiYhNSqr5X9AhUbGVkFHScnDU8QFnoECA8QAQ&url=https%3A%2F%2Fjournals.flvc.org%2Fsal%2Farticle%2Fdownload%2F107395%2F102715%2F&usg=AOvVaw25U3augVPmpZE1yX8PFevq NOUN CLASSIFICATION IN WOLOF: WHEN AFFIXES ARE NOT RENEWED]</ref>

*phonetic study of Wolof in Senegal and The Gambia<ref>[https://doi.org/10.2307/1155382 Short Phonetic Study]</ref> - all rights reserved
*Wolof lexicon and grammar<ref>[https://www.worldcat.org/title/681994315 Wolof lexicon and grammar]</ref> - all rights reserved
*Contemporary Wolof Grammar<ref>[https://www.worldcat.org/title/319212381 Grammaire du wolof contemporain]</ref> - all rights reserved
*Wolof learning manual for English speakers<ref>[https://www.worldcat.org/title/1346569670 Wolof learning manual for English speakers]</ref> - all rights reserved
*Introduction to Wolof grammar : English version = Roofoo-bi-baat<ref>[https://www.worldcat.org/title/877822775 Intro to Wolof Grammar]</ref> - all rights reserved
*Also listed under Peace Corps Wolof Resource Collection: [https://resourcepage.gambia.dk/ftp/wolfgram.pdf Wolof Grammar Manual]
*[https://resourcepage.gambia.dk/ftp/wolfgram.pdf Peace Corps: New Wolof Book]
*[http://wolofresources.org/language/download/grammar.pdf Wolof Grammar Resources]
*[https://hal.science/hal-01422883/document Content question words and noun class markers in Wolof: reconstructing a puzzle]

======Scientific works (papers, books, websites):======
*Wolof morphological analyzer<ref>[https://www.iaaw.hu-berlin.de/de/afrika/linguistik-und-sprachen/veranstaltungen/afrikalinguistischeskolloquium/papers-wintersemester-2011-12/a-morphological-analyzer-for-wolof-using-finite-state-techniques-handout morphological analyzer]</ref> - usage rights: not listed, but I assume we can use it if we cite it
*Sociolinguistic study on the impact of Coid-19 on Wolof in Senegal <ref>[https://www.ceeol.com/search/article-detail?id=995002 Sociolinguistic Study]</ref>

======Corpora (any collection of authentic text, linguistically annotated or not, including Wikipedia in the language, news websites, Twitter feeds, etc.)======
*Bible - not sure if this is Senegalese or Gambian Wolof yet<ref>[http://www.biblewolof.com/ Bible]</ref> - Creative Commons License, © 2010-2020 AES et MBS.
*2010 Bible Senegalese Wolof - this is James 1:1 to 5:20 <ref>[https://ebible.org/pdf/wol2010/wol2010_JAS.pdf 2010 wol Bible]</ref> - © 2010 La Mission Baptiste du Sénégal under creative commons license 4.0
*Wikipedia pages in Wolof <ref>[https://wo.wikipedia.org/wiki/Jagleel:Toutes_les_pages wolof wikipedia] </ref> (Creative Commons)
*Bible resources<ref>[http://wolofresources.org/language/olb.htm add properly later Bible resources]</ref> (usage rights in block quote below)
"The usual copyright restrictions apply to the use of these Scripture portions. For use of quotations of the Wolof Scriptures in published form, the text may be quoted in any form (written, visual, electronic or audio) up to and inclusive of 150 verses with written permission, providing the verses quoted do not amount to a complete book of the Bible nor do the verses quoted account for 25% or more of the total text of the work in which they are quoted. This permission is contingent upon an appropriate copyright acknowlegement. Use of the text beyond these limits requires written permission."
*2020 Revision of the Bible © 2023 Life.Church / YouVersion (terms of use allow us to use it<ref>[https://www.bible.com/terms Terms of Use]</ref>)<ref>[https://www.bible.com/bible/3338/GEN.1.KYG Life.Church Bible]</ref>

======New resources======
*Wolof corpus repository<ref>[https://github.swarthmore.edu/Ling073-sp23/ling073-wol-corpus Swarthmore Github Repository] </ref>

==Links==
[[Category:sp23_ResourceDocumentation]],[[Category:Wolof]]]

Sardinian and English

2023-05-05T19:04:44Z

Rorlija1: /* Final evaluation */

=Resources for Machine Translation from Sardinian to English=

==Developed Resources==
*[https://github.swarthmore.edu/Ling073-sp23/ling073-srd-eng-corpus Parallel corpus git repo].
*:Lines 1-8 from [http://maxia-mail.doomby.com/ this website].
*[https://github.swarthmore.edu/Ling073-sp23/ling073-srd-eng Git repo for language pair]
*[https://github.swarthmore.edu/Ling073-sp23/ling073-srd Git repo for Sardinian]
*[https://github.com/apertium/apertium-eng Forked git repo for English]
*[https://wikis.swarthmore.edu/ling073/Sardinian_and_English/Lexical_selection#srd_.E2.86.92_eng Lexical selection wiki]
*[https://wikis.swarthmore.edu/ling073/Sardinian_and_English/Contrastive_Grammar#Differences_in_parse_and_corresponding_examples Contrastive grammar wiki]
*[https://wikis.swarthmore.edu/ling073/Sardinian_and_English/Structural_transfer Structural transfer wiki]

==srd → eng evaluation==
*coverage of monolingual Sardinian transducer on srd.sentences.txt:
Number of tokenised words in the corpus: 262
Coverage: 94.66%
*coverage of bilingual transducer on srd.sentences
Number of tokenised words in the corpus: 266
Coverage: 85.71%

==Additions for polished RBMT system==
*Over 100 new stems to bilingual dictionary
*:(now we have 172 total entries in the .dix file)
*4 sets of lexical selection rules
*:(now we have rules that solve 5 problems in total)
*3 items from contrastive grammar implemented in transfer rules
*:(now we have rules that implement 4 total items)

==Final evaluation==
* For the monolingual transducer:
** Updated precision and recall against the (updated) <code>eval.test</code> and <code>eval.gold</code> files
** Coverage over the <code>large</code> corpus:
TOP UNKNOWN WORDS:
2336 ^po/*po$
1275 ^che/*che$
448 ^i/*i$
387 ^norte/*norte$
377 ^The/*The$
353 ^of/*of$
297 ^poi/*poi$
269 ^del/*del$
241 ^the/*the$
235 ^da/*da$
215 ^ch/*ch$
211 ^Il/*Il$
205 ^chentza/*chentza$
200 ^br/*br$
199 ^Arbaree/*Arbaree$
197 ^della/*della$
192 ^stètiu/*stètiu$
165 ^ddoi/*ddoi$
154 ^B/*B$
145 ^Norte/*Norte$
coverage: 1648134 / 1822907 (~0.90412401729764601266)

TOP UNKNOWN WORDS:
12208 ^cun/*cun$
8207 ^prus/*prus$
5205 ^o/*o$
4218 ^comente/*comente$
4100 ^fintzas/*fintzas$
3068 ^pustis/*pustis$
2658 ^annos/*annos$
2623 ^totu/*totu$
2589 ^ma/*ma$
2417 ^sua/*sua$
2376 ^parte/*parte$
2336 ^po/*po$
2250 ^Sardigna/*Sardigna$
2233 ^intre/*intre$
2120 ^ca/*ca$
2070 ^tzitade/*tzitade$
1964 ^che/*che$
1888 ^ue/*ue$
1873 ^bidda/*bidda$
1739 ^manera/*manera$
coverage: 963208 / 1863589 (~0.51685645279082458632)

** The number of words in the <code>large</code> corpus: ~1.85M words
** The number of stems in the transducer: ~85.5k stems

* For MT in the direction we developed (<code>srd-eng</code>):
** WER and PER over <code>longer</code> corpus:
-------------------------------------------------------
Number of words in reference: 315
Number of words in test: 341
Number of unknown words (marked with a star) in test: 35
Percentage of unknown words: 10.26 %

Results when removing unknown-word marks (stars)
-------------------------------------------------------
Edit distance: 246
Word error rate (WER): 78.10 %
Number of position-independent correct words: 118
Position-independent word error rate (PER): 70.79 %
** The proportion of stems translated correctly in the <code>longer</code> corpus.
118/341 = 34.6%
** Trimmed coverage over <code>longer</code> and <code>large</code> corpora.
** The number of tokens in <code>longer</code> and <code>large</code> corpora.
***<code>longer</code>: 341 tokens
***<code>large</code>: xxx tokens

==10 sentences glosses and outputs==
*Note: '''These are outputs at end of lexical transfer before lexical selection and other weeks' improvements were implemented'''
{| cellpadding=5
|Sardinian sentence || intended English translation || output of srd-eng-biltrans (lexical transfer) mode || output of srd-eng (full translation) mode
|-
|1) Su sardu est una limba antica. || Sardinian is an ancient language. || ^Su<det><def><m><sg>/The<det><def><m><sg>$ ^sardu<n><m><sg>/Sardinian<n><sg>$ ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$ ^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$^.<sent>/.<sent>$^.<sent>/.<sent>$
|| #The Sardinian #be #a language #ancient
|-
|2) Pro bider s'artìculu sighire custu culligamentu. || To read the article click on this link. || ^Pro<pr>/For<pr>/To<pr>$ ^bider<vblex><inf>/read<vblex><inf>$ ^su<det><def><mf><sg>/the<det><def><mf><sg>$ ^artìculu<n><m><sg>/article<n><sg>$ ^sighire<vblex><inf>/click<vblex><inf>$ ^custu<det><dem><m><sg>/this<det><m><sg>$ ^culligamentu<n><m><sg>/link<n><sg>$^.<sent>/.<sent>$^.<sent>/.<sent>$<m><sg>$ ^culligamentu<n><m><sg>/link<n><sg>$^.<sent>/.<sent>$^.<sent>/.<sent>$
|| For read #the article click #this link.
|-
|3) Su trenu sinke fit andande. || The train was leaving. || ^Su<det><def><m><sg>/The<det><def><m><sg>$ ^trenu<n><m><sg>/train<n><sg>$ ^sinke<cnjadv>/$ ^èssere<vbser><pii><p3><sg>/be<vbser><pii><p3><sg>$ ^andare<vblex><ger>/leave<vblex><ger>/go<vblex><ger>$^.<sent>/.<sent>$^.<sent>/.<sent>$

|| #The train #be leaving.
|-
|4) Su trenu at a arrivare a sas deke. || The train will arrive at ten. || ^Su<det><def><m><sg>/The<det><def><m><sg>$ ^trenu<n><m><sg>/train<n><sg>$ ^àere<vbhaver><pri><p3><sg>/have<vbhaver><pri><p3><sg>$ ^a<pr>/at<pr>/on<pr>/to<pr>$ ^arrivare<vblex><inf>/arrive<vblex><inf>$ ^a<pr>/at<pr>/on<pr>/to<pr>$ ^su<det><def><f><pl>/the<det><def><f><pl>$ ^deke<num><mf><sp>/ten<num><mf><sp>$^.<sent>/.<sent>$^.<sent>/.<sent>$
|| #The train #have at arrive at #the #ten.
|-
|5) Su trenu devet arrivare a sas deke. || The train should arrive at ten. || ^Su<det><def><m><sg>/The<det><def><m><sg>$ ^trenu<n><m><sg>/train<n><sg>$ ^dèvere<vblex><pri><p3><sg>/shall<vbmod><pri><p3><sg>$ ^arrivare<vblex><inf>/arrive<vblex><inf>$ ^a<pr>/at<pr>/on<pr>/to<pr>$ ^su<det><def><f><pl>/the<det><def><f><pl>$ ^deke<num><mf><sp>/ten<num><mf><sp>$^.<sent>/.<sent>$^.<sent>/.<sent>$
|| #The train #shall arrive at #the #ten.
|-
|6) T'appo natu ki su trenu devíat arrivare a sas deke. || I told you that the train would arrive at ten. || ^Ti<prn><pro><p2><mf><sg>/You<prn><pro><p2><mf><sg>$ ^àere<vbhaver><pri><p1><sg>/have<vbhaver><pri><p1><sg>$ ^nàrrere<vblex><pp><m><sg>/tell<vblex><pp><m><sg>$ ^chi<cnjsub>/that<cnjsub>$ ^su<det><def><m><sg>/the<det><def><m><sg>$ ^trenu<n><m><sg>/train<n><sg>$ ^dèvere<vblex><pii><p3><sg>/shall<vbmod><pii><p3><sg>$ ^arrivare<vblex><inf>/arrive<vblex><inf>$ ^a<pr>/at<pr>/on<pr>/to<pr>$ ^su<det><def><f><pl>/the<det><def><f><pl>$ ^deke<num><mf><sp>/ten<num><mf><sp>$^.<sent>/.<sent>$^.<sent>/.<sent>$
|| #You #have #tell that #the train #shall arrive at #the #ten.
|-
|7) No'isco si at a pròere cras. || I do not know if it will rain tomorrow. || ^No<adv>/Not<adv>$'^iscoare<vblex><pri><p1><sg>/know<vblex><pri><p1><sg>$ ^si<cnjsub>/if<cnjsub>$ ^àere<vbhaver><pri><p3><sg>/have<vbhaver><pri><p3><sg>$ ^a<pr>/at<pr>/on<pr>/to<pr>$ ^pròere<vblex><inf>/rain<vblex><inf>$ ^cras<adv>/tomorrow<adv>$^.<sent>/.<sent>$
|| Not'#know if #have at rain tomorrow

|-
|8) Una de sas berbekes est maláida. || One of the sheep is sick. || ^Unu<num><f><sp>/One<num><f><sp>$ ^de<pr>/to<pr>/of<pr>$ ^su<det><def><f><pl>/the<det><def><f><pl>$ ^berbeke<n><f><pl>/sheep<n><pl>$ ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$ ^malàidu<adj><f><sg>/sick<adj><f><sg>$^.<sent>/.<sent>$
|| #One to #the sheep #be #sick

|-
|9) Appo pèrditu duos de sos libros meos. || I have lost two of my books. || ^Àere<vbhaver><pri><p1><sg>/Have<vbhaver><pri><p1><sg>$ ^pèrdere<vblex><pp><m><sg>/lose<vblex><pp><m><sg>$ ^duos<num><m><sp>/two<num><m><sp>$ ^de<pr>/to<pr>/of<pr>$ ^su<det><def><m><pl>/the<det><def><m><pl>$ ^libru<n><m><pl>/book<n><pl>$ ^meu<prn><pos><m><pl>/my<prn><pos><m><pl>$^.<sent>/.<sent>$

|| #Have #lose #two to #the books #my

|-
|10) M'an natu ki su trenu devíat arrivare a sas nove. || They told me that the train was supposed to arrive at nine. || ^Mi<prn><pro><p1><mf><sg>/I<prn><pro><p1><mf><sg>$ ^àere<vbhaver><pri><p3><pl>/have<vbhaver><pri><p3><pl>$ ^nàrrere<vblex><pp><m><sg>/tell<vblex><pp><m><sg>$ ^chi<cnjsub>/that<cnjsub>$ ^su<det><def><m><sg>/the<det><def><m><sg>$ ^trenu<n><m><sg>/train<n><sg>$ ^dèvere<vblex><pii><p3><sg>/shall<vbmod><pii><p3><sg>$ ^arrivare<vblex><inf>/arrive<vblex><inf>$ ^a<pr>/at<pr>/on<pr>/to<pr>$ ^su<det><def><f><pl>/the<det><def><f><pl>$ ^nove<num><mf><sp>/nine<num><mf><sp>$^.<sent>/.<sent>$
|| #I #have #tell that #the train #shall arrive at #the #nine
|
|}

==expanding lexicon==

{| cellpadding=5
|medas || many || <adj>
|-https://wikis.swarthmore.edu/ling073/index.php?title=Sardinian_and_English&action=edit
|piseddas || girls || <n><pl>
|-
|sun || they are || <v>
|-
|bennidas || to come (home) || <v><pp><fpl>
|-
|balladu || to dance || <v><pp>
|-
|cantaiat || to sing || <v><sg3>
|-
|sos/sa || the || <det>
|-
|piattos || plates || <n><pl>
|-
|mesa || table || <n><sg>
|-
|bi/b' || N/A || <cl>
|-
|problemas || problems || <n><pl>
|-
|unu || one/a || <adj>/<det>
|-
|ube || where || <adv>
|-
|mortu || dead || <v><pp>
|-
|sordatos || soldiers || <n><pl>
|-
|tenimus || we have || <v><pl1>
|-
|frores || flowers || <n><pl>
|-
|keret || to be necessary || <v><sg3>
|-
|mancat || to be missing || <v><sg3>
|-
|ovos || eggs || <n><pl>
|-
|danca || meadow || <n>
|-
|ortu || orchard || <n>
|-
|frade || brother || <n>
|-
|fizza || daughter || <n>
|-
|re || king || <n>
|-
|ora || hour || <n>
|-
|subra || above/on || <prep>
|-
|a || to/at || <prep>
|-
|cumintzos || origins || <n><pl>
|-
|e || and || <conj>
|-
|andamentu || evolution || <n>
|-
|istòricu || historical || <adj>
|-
|de || of/to || <prep>
|-
|sa || the || <det>
|-
|poesia || poetry || <n>
|-
|a bolu || improvised || <adj> (a bolu = improvised, on the fly)
|-
|in || in || <prep>
|-
|sardu || Sardinian || <n>
|-
|logudoresu || Logudorese || <adj>
|-
|non || not || <adv>
|-
|ischit || known || <v><pp>
|-
|meda || much || <adv>
|-
|custu || this || <det><prox>
|-
|artìculu || article || <n>
|-
|chircat || tries || <v><sg3>
|-
|bogare || to bring out || <v>
|-
|pizu || surface || <n> (bogare a pizu = to shed light on, to bring to the surface; see complicated translations of bogare: [http://vocabolariocasu.isresardegna.it/index.php?key=b&int=0&lemmi=cerca&codice=b1264000 here])
|-
|ammentos || memories || <n><pl>
|-
|ammentu || memory || <n>
|-
|ammentare || to remember || <v>
|-
|documentados || documented || <adj>
|-
|si || [null] || <> -- reflexive
|-
|primas || first || <adj>
|-
|disputas || competitions || <n><pl>
|-
|primas || first || <adj>
|-
|tra || between || <prep>
|-
|poetes || poets || <n><pl>
|-
|cale || which || <prn><rel>
|-
|esserent || were || <v> past imperfect 3rd person plural
|-
|règulas || rules, modalities || <n><pl>
|-
|su || the || <det>
|-
|cunfruntu || confrontation || <n>
|-
|sende || being || <v><ger>
|-
|una || a/one || <art>/<adj>
|-
|chirca || research || <n>
|-
|andera || ongoing/progressive || <adj>
|-
|testu || text || <n>
|-
|diat || [null] || <subj><sg3>
|-
|poder || to be able to || <v><inf>
|-
|aer || to have || <v><inf> (also hàere or àere)
|-
|mudonzos || modifications || <n><pl>
|-
|mudonzos || modifications || <n><pl>
|-
|novas || new || <adj><pl>
|-
|noas || data || <n><pl>
|-
|Pro || to || <prep> <-- keep this in mind for lexical selection (to)
|-
|bider || to read || <v><inf>
|-
|artìculu || article || <n>
|-
|sighire || click on || <v><inf>
|-
|intrare || enter || <v><inf>
|-
|desizadu || desired || <adj>
|-
|trenu || train || <n>
|-
|sinke || [null] || <foc>
|-
|fit || was || <v><imp><sg3>
|-
|andande || leaving || <v><ger>
|-
|at || it will || <>
|-
|sas || the || <det>
|-
|deke || ten || <n>
|-
|devet || should || <adv>
|-
|deke || ten || <adj>
|-
|appo || I have || <v><sg1>
|-
|natu || told || <v><pp>
|-
|próere || to rain || <v><inf>
|-
|arrivare || to arrive || <v><inf>
|-
|isco || I know || <v><sg1>
|-
|si || if || <conj>
|-
|ki || that || <conj>
|-
|cras || tomorrow || <adv>
|-
|meos || my || <pos>
|-
|andatos || gone || <adj><pl>
|
|}

===glosses===

Cando so arrivatu a s'istazione, su trenu sink'andaiat

'when I arrived at the station, the train was leaving'

Su trenu sinke fit andande

'The train was leaving"

Su trenu at a arrivare a sas deke

'The train will arrive at ten o'clock'

Su trenu devet arrivare a sas deke

'The train is supposed to arrive at ten o'clock'

T'appo natu ki su trenu diat arrivare a sas deke

'I told you that the train would arrive at ten o'clock'

M'an natu ki su trenu devíat arrivare a sas nove

'They told me that the train was supposed to arrive at nine'

At a próere cras

'It will rain tomorrow'

Devet próere cras

'it is supposed to rain tomorrow'

At a próere cras? Si emmo abbarramus in domo, ma su nono andamus a mare

'Will it rain tomorrow? If so we shall stay at homr, buy if not we will go to the sea'

No'isco si at a próere cras

'I do to know whether it will rain tomorrow'

Una de sas berbekes est maláida

'one of the sheep is sick'

Appo pèrditu duos de sos libros meos

'I have lost two of my books'

Metas de custas pitzinnas sun galanas

'Many of these girls are pretty'

Una pitzinna meta bella

'a very beautiful girl'

Cussas duas bravas pitzinnas

'those two good girls'

unu better cane bellu

'a huge beautiful dog'

un'átteru bette cane

'another huge dog'

Sun andatos a Frantza

'they went to France'

Est ghiratu dae Corsica

'He returned from Corsica'

Connnosco bene sa Frantza

"i know France well'

Custu libru est iscrittu in tedescu

'This book is written in German'

Cussus paráula venit dae su catalanu

'This word comes from Catalan'

Su sardu est una limba antica

'Sardinian is an ancient language'

Appo mandicatu casu

'I ate cheese'

Laura est toddende frores

'Laura is picking flowers'

De frores non nd'appo tódditu

'I did not pick any flowers'

No'amus comporatu pane

'We did not buy bread'

Mandico sa pasta kin casu

'I ate pasta with cheese'

Tres sórrikes an mandicatu tottu su casu

'Three mice ate all the cheese'

semus ponnende vinu in ampullas

'We are putting wine in bottles'

lettu meu esr

'It is my bed'

No'appo lessu libru perunu

'i did not read any book'

Sos k'an furatu si dinari at a èssere punitos

'The people who stole the money will be punished'

Appo invitat sos de Juanne

'I invited Jon's family'

Cussa pinna est sa mea

'That pen is mine'

Cudda mákkina est sa de Juanne

'That car is John's'

Custa ricca at datu mili francos a su vetzu

'This rich woman gave a thousand lira to the old man'

Su guvernu devíat dare ua pensione a dondzi vetzu

'The government should give a pension to every old person'

==External Resources==

*Github repository for [https://github.com/apertium/apertium-srd Sardinian transducer] (and our [https://github.swarthmore.edu/Ling073-sp23/ling073-srd clone])
*Github repository for [https://github.com/apertium/apertium-eng English transducer]
*[https://www.limbasardasudsardigna.it/sar/images/Documenti/Didatica_e_Ainas/Ditzion%C3%A0riu%20Universale%20Rubattu.pdf Dictionary pdf]
*[http://ditzionariu.sardegnacultura.it/it/ Online official dictionary]
*[https://it.glosbe.com/sc/it Web-based machine translator]
*[http://vocabolariocasu.isresardegna.it/index.php?key=a&int=0&lemmi=cerca Sardinian-Italian web-based dictionary]
*[http://www.sardegnadigitallibrary.it/mmt/fullsize/2009050512495700047.pdf 1931 pdf with select translations]
*[https://onlinelibrary.wiley.com/doi/epdf/10.1111/j.0079-1636.2004.00130.x Definiteness effects: evidence from Sardinian]
*[https://www.icongrouponline.com/en/Detail/dictionary/049783698X/Webster%27s+Sardinian+-+English+Thesaurus+Dictionary: Webster's Sardinian English Thesaurus Dictionary]
*[https://www.academia.edu/15320922/Dizionario_della_lingua_Sarda_Vol_2 Italian-Sardinian Dictionary]
*[https://archive.org/details/vocabolariosardo00spanuoft/page/n361/mode/2up Old but extensive Sardo-Italian and vice versa dictionary]
*[https://limbasardasudsardigna.it/sar/images/Documenti/Didatica_e_Ainas/Vocabolariu_Sardu_Italianu_Spano.pdf nice Sardo-Italiano dictionary pdf]
*[http://www.fontesarda.it/sr/sr0045.htm Conjugations of "to have" in Sardinian]
*[https://sinnainotizie.com/2015/03/07/lezioni-di-grammatica-sardo-campidanese-undicesima-lezione-su-verbu-ai-aere/ Whole Sardinian grammar page about conjugations of to have all written in Sardinian language!]
*Sardinian grammar:[https://www.limbasardasudsardigna.it/sar/images/Documenti/Didatica_e_Ainas/grammatiga_sardo%20campidanese%20A.LEPORI.pdf pdf]
[[Category:Sp23_TranslationPairs]],[[Category:Sardinian]],[[Category:English]]

Sardinian and English

2023-05-05T18:59:08Z

Rorlija1: /* Final evaluation */

=Resources for Machine Translation from Sardinian to English=

==Developed Resources==
*[https://github.swarthmore.edu/Ling073-sp23/ling073-srd-eng-corpus Parallel corpus git repo].
*:Lines 1-8 from [http://maxia-mail.doomby.com/ this website].
*[https://github.swarthmore.edu/Ling073-sp23/ling073-srd-eng Git repo for language pair]
*[https://github.swarthmore.edu/Ling073-sp23/ling073-srd Git repo for Sardinian]
*[https://github.com/apertium/apertium-eng Forked git repo for English]
*[https://wikis.swarthmore.edu/ling073/Sardinian_and_English/Lexical_selection#srd_.E2.86.92_eng Lexical selection wiki]
*[https://wikis.swarthmore.edu/ling073/Sardinian_and_English/Contrastive_Grammar#Differences_in_parse_and_corresponding_examples Contrastive grammar wiki]
*[https://wikis.swarthmore.edu/ling073/Sardinian_and_English/Structural_transfer Structural transfer wiki]

==srd → eng evaluation==
*coverage of monolingual Sardinian transducer on srd.sentences.txt:
Number of tokenised words in the corpus: 262
Coverage: 94.66%
*coverage of bilingual transducer on srd.sentences
Number of tokenised words in the corpus: 266
Coverage: 85.71%

==Additions for polished RBMT system==
*Over 100 new stems to bilingual dictionary
*:(now we have 172 total entries in the .dix file)
*4 sets of lexical selection rules
*:(now we have rules that solve 5 problems in total)
*3 items from contrastive grammar implemented in transfer rules
*:(now we have rules that implement 4 total items)

==Final evaluation==
* For the monolingual transducer:
** Updated precision and recall against the (updated) <code>eval.test</code> and <code>eval.gold</code> files
** Coverage over the <code>large</code> corpus:
TOP UNKNOWN WORDS:
2336 ^po/*po$
1275 ^che/*che$
448 ^i/*i$
387 ^norte/*norte$
377 ^The/*The$
353 ^of/*of$
297 ^poi/*poi$
269 ^del/*del$
241 ^the/*the$
235 ^da/*da$
215 ^ch/*ch$
211 ^Il/*Il$
205 ^chentza/*chentza$
200 ^br/*br$
199 ^Arbaree/*Arbaree$
197 ^della/*della$
192 ^stètiu/*stètiu$
165 ^ddoi/*ddoi$
154 ^B/*B$
145 ^Norte/*Norte$
coverage: 1648134 / 1822907 (~0.90412401729764601266)

TOP UNKNOWN WORDS:
12208 ^cun/*cun$
8207 ^prus/*prus$
5205 ^o/*o$
4218 ^comente/*comente$
4100 ^fintzas/*fintzas$
3068 ^pustis/*pustis$
2658 ^annos/*annos$
2623 ^totu/*totu$
2589 ^ma/*ma$
2417 ^sua/*sua$
2376 ^parte/*parte$
2336 ^po/*po$
2250 ^Sardigna/*Sardigna$
2233 ^intre/*intre$
2120 ^ca/*ca$
2070 ^tzitade/*tzitade$
1964 ^che/*che$
1888 ^ue/*ue$
1873 ^bidda/*bidda$
1739 ^manera/*manera$
coverage: 963208 / 1863589 (~0.51685645279082458632)

** The number of words in the <code>large</code> corpus: ~1.85M words
** The number of stems in the transducer.

* For MT in the direction we developed (<code>srd-eng</code>):
** WER and PER over <code>longer</code> corpus:
-------------------------------------------------------
Number of words in reference: 315
Number of words in test: 341
Number of unknown words (marked with a star) in test: 35
Percentage of unknown words: 10.26 %

Results when removing unknown-word marks (stars)
-------------------------------------------------------
Edit distance: 246
Word error rate (WER): 78.10 %
Number of position-independent correct words: 118
Position-independent word error rate (PER): 70.79 %
** The proportion of stems translated correctly in the <code>longer</code> corpus.
118/341 = 34.6%
** Trimmed coverage over <code>longer</code> and <code>large</code> corpora.
** The number of tokens in <code>longer</code> and <code>large</code> corpora.
***<code>longer</code>: 341 tokens
***<code>large</code>: xxx tokens

==10 sentences glosses and outputs==
*Note: '''These are outputs at end of lexical transfer before lexical selection and other weeks' improvements were implemented'''
{| cellpadding=5
|Sardinian sentence || intended English translation || output of srd-eng-biltrans (lexical transfer) mode || output of srd-eng (full translation) mode
|-
|1) Su sardu est una limba antica. || Sardinian is an ancient language. || ^Su<det><def><m><sg>/The<det><def><m><sg>$ ^sardu<n><m><sg>/Sardinian<n><sg>$ ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$ ^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$^.<sent>/.<sent>$^.<sent>/.<sent>$
|| #The Sardinian #be #a language #ancient
|-
|2) Pro bider s'artìculu sighire custu culligamentu. || To read the article click on this link. || ^Pro<pr>/For<pr>/To<pr>$ ^bider<vblex><inf>/read<vblex><inf>$ ^su<det><def><mf><sg>/the<det><def><mf><sg>$ ^artìculu<n><m><sg>/article<n><sg>$ ^sighire<vblex><inf>/click<vblex><inf>$ ^custu<det><dem><m><sg>/this<det><m><sg>$ ^culligamentu<n><m><sg>/link<n><sg>$^.<sent>/.<sent>$^.<sent>/.<sent>$<m><sg>$ ^culligamentu<n><m><sg>/link<n><sg>$^.<sent>/.<sent>$^.<sent>/.<sent>$
|| For read #the article click #this link.
|-
|3) Su trenu sinke fit andande. || The train was leaving. || ^Su<det><def><m><sg>/The<det><def><m><sg>$ ^trenu<n><m><sg>/train<n><sg>$ ^sinke<cnjadv>/$ ^èssere<vbser><pii><p3><sg>/be<vbser><pii><p3><sg>$ ^andare<vblex><ger>/leave<vblex><ger>/go<vblex><ger>$^.<sent>/.<sent>$^.<sent>/.<sent>$

|| #The train #be leaving.
|-
|4) Su trenu at a arrivare a sas deke. || The train will arrive at ten. || ^Su<det><def><m><sg>/The<det><def><m><sg>$ ^trenu<n><m><sg>/train<n><sg>$ ^àere<vbhaver><pri><p3><sg>/have<vbhaver><pri><p3><sg>$ ^a<pr>/at<pr>/on<pr>/to<pr>$ ^arrivare<vblex><inf>/arrive<vblex><inf>$ ^a<pr>/at<pr>/on<pr>/to<pr>$ ^su<det><def><f><pl>/the<det><def><f><pl>$ ^deke<num><mf><sp>/ten<num><mf><sp>$^.<sent>/.<sent>$^.<sent>/.<sent>$
|| #The train #have at arrive at #the #ten.
|-
|5) Su trenu devet arrivare a sas deke. || The train should arrive at ten. || ^Su<det><def><m><sg>/The<det><def><m><sg>$ ^trenu<n><m><sg>/train<n><sg>$ ^dèvere<vblex><pri><p3><sg>/shall<vbmod><pri><p3><sg>$ ^arrivare<vblex><inf>/arrive<vblex><inf>$ ^a<pr>/at<pr>/on<pr>/to<pr>$ ^su<det><def><f><pl>/the<det><def><f><pl>$ ^deke<num><mf><sp>/ten<num><mf><sp>$^.<sent>/.<sent>$^.<sent>/.<sent>$
|| #The train #shall arrive at #the #ten.
|-
|6) T'appo natu ki su trenu devíat arrivare a sas deke. || I told you that the train would arrive at ten. || ^Ti<prn><pro><p2><mf><sg>/You<prn><pro><p2><mf><sg>$ ^àere<vbhaver><pri><p1><sg>/have<vbhaver><pri><p1><sg>$ ^nàrrere<vblex><pp><m><sg>/tell<vblex><pp><m><sg>$ ^chi<cnjsub>/that<cnjsub>$ ^su<det><def><m><sg>/the<det><def><m><sg>$ ^trenu<n><m><sg>/train<n><sg>$ ^dèvere<vblex><pii><p3><sg>/shall<vbmod><pii><p3><sg>$ ^arrivare<vblex><inf>/arrive<vblex><inf>$ ^a<pr>/at<pr>/on<pr>/to<pr>$ ^su<det><def><f><pl>/the<det><def><f><pl>$ ^deke<num><mf><sp>/ten<num><mf><sp>$^.<sent>/.<sent>$^.<sent>/.<sent>$
|| #You #have #tell that #the train #shall arrive at #the #ten.
|-
|7) No'isco si at a pròere cras. || I do not know if it will rain tomorrow. || ^No<adv>/Not<adv>$'^iscoare<vblex><pri><p1><sg>/know<vblex><pri><p1><sg>$ ^si<cnjsub>/if<cnjsub>$ ^àere<vbhaver><pri><p3><sg>/have<vbhaver><pri><p3><sg>$ ^a<pr>/at<pr>/on<pr>/to<pr>$ ^pròere<vblex><inf>/rain<vblex><inf>$ ^cras<adv>/tomorrow<adv>$^.<sent>/.<sent>$
|| Not'#know if #have at rain tomorrow

|-
|8) Una de sas berbekes est maláida. || One of the sheep is sick. || ^Unu<num><f><sp>/One<num><f><sp>$ ^de<pr>/to<pr>/of<pr>$ ^su<det><def><f><pl>/the<det><def><f><pl>$ ^berbeke<n><f><pl>/sheep<n><pl>$ ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$ ^malàidu<adj><f><sg>/sick<adj><f><sg>$^.<sent>/.<sent>$
|| #One to #the sheep #be #sick

|-
|9) Appo pèrditu duos de sos libros meos. || I have lost two of my books. || ^Àere<vbhaver><pri><p1><sg>/Have<vbhaver><pri><p1><sg>$ ^pèrdere<vblex><pp><m><sg>/lose<vblex><pp><m><sg>$ ^duos<num><m><sp>/two<num><m><sp>$ ^de<pr>/to<pr>/of<pr>$ ^su<det><def><m><pl>/the<det><def><m><pl>$ ^libru<n><m><pl>/book<n><pl>$ ^meu<prn><pos><m><pl>/my<prn><pos><m><pl>$^.<sent>/.<sent>$

|| #Have #lose #two to #the books #my

|-
|10) M'an natu ki su trenu devíat arrivare a sas nove. || They told me that the train was supposed to arrive at nine. || ^Mi<prn><pro><p1><mf><sg>/I<prn><pro><p1><mf><sg>$ ^àere<vbhaver><pri><p3><pl>/have<vbhaver><pri><p3><pl>$ ^nàrrere<vblex><pp><m><sg>/tell<vblex><pp><m><sg>$ ^chi<cnjsub>/that<cnjsub>$ ^su<det><def><m><sg>/the<det><def><m><sg>$ ^trenu<n><m><sg>/train<n><sg>$ ^dèvere<vblex><pii><p3><sg>/shall<vbmod><pii><p3><sg>$ ^arrivare<vblex><inf>/arrive<vblex><inf>$ ^a<pr>/at<pr>/on<pr>/to<pr>$ ^su<det><def><f><pl>/the<det><def><f><pl>$ ^nove<num><mf><sp>/nine<num><mf><sp>$^.<sent>/.<sent>$
|| #I #have #tell that #the train #shall arrive at #the #nine
|
|}

==expanding lexicon==

{| cellpadding=5
|medas || many || <adj>
|-https://wikis.swarthmore.edu/ling073/index.php?title=Sardinian_and_English&action=edit
|piseddas || girls || <n><pl>
|-
|sun || they are || <v>
|-
|bennidas || to come (home) || <v><pp><fpl>
|-
|balladu || to dance || <v><pp>
|-
|cantaiat || to sing || <v><sg3>
|-
|sos/sa || the || <det>
|-
|piattos || plates || <n><pl>
|-
|mesa || table || <n><sg>
|-
|bi/b' || N/A || <cl>
|-
|problemas || problems || <n><pl>
|-
|unu || one/a || <adj>/<det>
|-
|ube || where || <adv>
|-
|mortu || dead || <v><pp>
|-
|sordatos || soldiers || <n><pl>
|-
|tenimus || we have || <v><pl1>
|-
|frores || flowers || <n><pl>
|-
|keret || to be necessary || <v><sg3>
|-
|mancat || to be missing || <v><sg3>
|-
|ovos || eggs || <n><pl>
|-
|danca || meadow || <n>
|-
|ortu || orchard || <n>
|-
|frade || brother || <n>
|-
|fizza || daughter || <n>
|-
|re || king || <n>
|-
|ora || hour || <n>
|-
|subra || above/on || <prep>
|-
|a || to/at || <prep>
|-
|cumintzos || origins || <n><pl>
|-
|e || and || <conj>
|-
|andamentu || evolution || <n>
|-
|istòricu || historical || <adj>
|-
|de || of/to || <prep>
|-
|sa || the || <det>
|-
|poesia || poetry || <n>
|-
|a bolu || improvised || <adj> (a bolu = improvised, on the fly)
|-
|in || in || <prep>
|-
|sardu || Sardinian || <n>
|-
|logudoresu || Logudorese || <adj>
|-
|non || not || <adv>
|-
|ischit || known || <v><pp>
|-
|meda || much || <adv>
|-
|custu || this || <det><prox>
|-
|artìculu || article || <n>
|-
|chircat || tries || <v><sg3>
|-
|bogare || to bring out || <v>
|-
|pizu || surface || <n> (bogare a pizu = to shed light on, to bring to the surface; see complicated translations of bogare: [http://vocabolariocasu.isresardegna.it/index.php?key=b&int=0&lemmi=cerca&codice=b1264000 here])
|-
|ammentos || memories || <n><pl>
|-
|ammentu || memory || <n>
|-
|ammentare || to remember || <v>
|-
|documentados || documented || <adj>
|-
|si || [null] || <> -- reflexive
|-
|primas || first || <adj>
|-
|disputas || competitions || <n><pl>
|-
|primas || first || <adj>
|-
|tra || between || <prep>
|-
|poetes || poets || <n><pl>
|-
|cale || which || <prn><rel>
|-
|esserent || were || <v> past imperfect 3rd person plural
|-
|règulas || rules, modalities || <n><pl>
|-
|su || the || <det>
|-
|cunfruntu || confrontation || <n>
|-
|sende || being || <v><ger>
|-
|una || a/one || <art>/<adj>
|-
|chirca || research || <n>
|-
|andera || ongoing/progressive || <adj>
|-
|testu || text || <n>
|-
|diat || [null] || <subj><sg3>
|-
|poder || to be able to || <v><inf>
|-
|aer || to have || <v><inf> (also hàere or àere)
|-
|mudonzos || modifications || <n><pl>
|-
|mudonzos || modifications || <n><pl>
|-
|novas || new || <adj><pl>
|-
|noas || data || <n><pl>
|-
|Pro || to || <prep> <-- keep this in mind for lexical selection (to)
|-
|bider || to read || <v><inf>
|-
|artìculu || article || <n>
|-
|sighire || click on || <v><inf>
|-
|intrare || enter || <v><inf>
|-
|desizadu || desired || <adj>
|-
|trenu || train || <n>
|-
|sinke || [null] || <foc>
|-
|fit || was || <v><imp><sg3>
|-
|andande || leaving || <v><ger>
|-
|at || it will || <>
|-
|sas || the || <det>
|-
|deke || ten || <n>
|-
|devet || should || <adv>
|-
|deke || ten || <adj>
|-
|appo || I have || <v><sg1>
|-
|natu || told || <v><pp>
|-
|próere || to rain || <v><inf>
|-
|arrivare || to arrive || <v><inf>
|-
|isco || I know || <v><sg1>
|-
|si || if || <conj>
|-
|ki || that || <conj>
|-
|cras || tomorrow || <adv>
|-
|meos || my || <pos>
|-
|andatos || gone || <adj><pl>
|
|}

===glosses===

Cando so arrivatu a s'istazione, su trenu sink'andaiat

'when I arrived at the station, the train was leaving'

Su trenu sinke fit andande

'The train was leaving"

Su trenu at a arrivare a sas deke

'The train will arrive at ten o'clock'

Su trenu devet arrivare a sas deke

'The train is supposed to arrive at ten o'clock'

T'appo natu ki su trenu diat arrivare a sas deke

'I told you that the train would arrive at ten o'clock'

M'an natu ki su trenu devíat arrivare a sas nove

'They told me that the train was supposed to arrive at nine'

At a próere cras

'It will rain tomorrow'

Devet próere cras

'it is supposed to rain tomorrow'

At a próere cras? Si emmo abbarramus in domo, ma su nono andamus a mare

'Will it rain tomorrow? If so we shall stay at homr, buy if not we will go to the sea'

No'isco si at a próere cras

'I do to know whether it will rain tomorrow'

Una de sas berbekes est maláida

'one of the sheep is sick'

Appo pèrditu duos de sos libros meos

'I have lost two of my books'

Metas de custas pitzinnas sun galanas

'Many of these girls are pretty'

Una pitzinna meta bella

'a very beautiful girl'

Cussas duas bravas pitzinnas

'those two good girls'

unu better cane bellu

'a huge beautiful dog'

un'átteru bette cane

'another huge dog'

Sun andatos a Frantza

'they went to France'

Est ghiratu dae Corsica

'He returned from Corsica'

Connnosco bene sa Frantza

"i know France well'

Custu libru est iscrittu in tedescu

'This book is written in German'

Cussus paráula venit dae su catalanu

'This word comes from Catalan'

Su sardu est una limba antica

'Sardinian is an ancient language'

Appo mandicatu casu

'I ate cheese'

Laura est toddende frores

'Laura is picking flowers'

De frores non nd'appo tódditu

'I did not pick any flowers'

No'amus comporatu pane

'We did not buy bread'

Mandico sa pasta kin casu

'I ate pasta with cheese'

Tres sórrikes an mandicatu tottu su casu

'Three mice ate all the cheese'

semus ponnende vinu in ampullas

'We are putting wine in bottles'

lettu meu esr

'It is my bed'

No'appo lessu libru perunu

'i did not read any book'

Sos k'an furatu si dinari at a èssere punitos

'The people who stole the money will be punished'

Appo invitat sos de Juanne

'I invited Jon's family'

Cussa pinna est sa mea

'That pen is mine'

Cudda mákkina est sa de Juanne

'That car is John's'

Custa ricca at datu mili francos a su vetzu

'This rich woman gave a thousand lira to the old man'

Su guvernu devíat dare ua pensione a dondzi vetzu

'The government should give a pension to every old person'

==External Resources==

*Github repository for [https://github.com/apertium/apertium-srd Sardinian transducer] (and our [https://github.swarthmore.edu/Ling073-sp23/ling073-srd clone])
*Github repository for [https://github.com/apertium/apertium-eng English transducer]
*[https://www.limbasardasudsardigna.it/sar/images/Documenti/Didatica_e_Ainas/Ditzion%C3%A0riu%20Universale%20Rubattu.pdf Dictionary pdf]
*[http://ditzionariu.sardegnacultura.it/it/ Online official dictionary]
*[https://it.glosbe.com/sc/it Web-based machine translator]
*[http://vocabolariocasu.isresardegna.it/index.php?key=a&int=0&lemmi=cerca Sardinian-Italian web-based dictionary]
*[http://www.sardegnadigitallibrary.it/mmt/fullsize/2009050512495700047.pdf 1931 pdf with select translations]
*[https://onlinelibrary.wiley.com/doi/epdf/10.1111/j.0079-1636.2004.00130.x Definiteness effects: evidence from Sardinian]
*[https://www.icongrouponline.com/en/Detail/dictionary/049783698X/Webster%27s+Sardinian+-+English+Thesaurus+Dictionary: Webster's Sardinian English Thesaurus Dictionary]
*[https://www.academia.edu/15320922/Dizionario_della_lingua_Sarda_Vol_2 Italian-Sardinian Dictionary]
*[https://archive.org/details/vocabolariosardo00spanuoft/page/n361/mode/2up Old but extensive Sardo-Italian and vice versa dictionary]
*[https://limbasardasudsardigna.it/sar/images/Documenti/Didatica_e_Ainas/Vocabolariu_Sardu_Italianu_Spano.pdf nice Sardo-Italiano dictionary pdf]
*[http://www.fontesarda.it/sr/sr0045.htm Conjugations of "to have" in Sardinian]
*[https://sinnainotizie.com/2015/03/07/lezioni-di-grammatica-sardo-campidanese-undicesima-lezione-su-verbu-ai-aere/ Whole Sardinian grammar page about conjugations of to have all written in Sardinian language!]
*Sardinian grammar:[https://www.limbasardasudsardigna.it/sar/images/Documenti/Didatica_e_Ainas/grammatiga_sardo%20campidanese%20A.LEPORI.pdf pdf]
[[Category:Sp23_TranslationPairs]],[[Category:Sardinian]],[[Category:English]]

Sardinian and English

2023-05-05T18:56:51Z

Rorlija1: /* Final evaluation */

=Resources for Machine Translation from Sardinian to English=

==Developed Resources==
*[https://github.swarthmore.edu/Ling073-sp23/ling073-srd-eng-corpus Parallel corpus git repo].
*:Lines 1-8 from [http://maxia-mail.doomby.com/ this website].
*[https://github.swarthmore.edu/Ling073-sp23/ling073-srd-eng Git repo for language pair]
*[https://github.swarthmore.edu/Ling073-sp23/ling073-srd Git repo for Sardinian]
*[https://github.com/apertium/apertium-eng Forked git repo for English]
*[https://wikis.swarthmore.edu/ling073/Sardinian_and_English/Lexical_selection#srd_.E2.86.92_eng Lexical selection wiki]
*[https://wikis.swarthmore.edu/ling073/Sardinian_and_English/Contrastive_Grammar#Differences_in_parse_and_corresponding_examples Contrastive grammar wiki]
*[https://wikis.swarthmore.edu/ling073/Sardinian_and_English/Structural_transfer Structural transfer wiki]

==srd → eng evaluation==
*coverage of monolingual Sardinian transducer on srd.sentences.txt:
Number of tokenised words in the corpus: 262
Coverage: 94.66%
*coverage of bilingual transducer on srd.sentences
Number of tokenised words in the corpus: 266
Coverage: 85.71%

==Additions for polished RBMT system==
*Over 100 new stems to bilingual dictionary
*:(now we have 172 total entries in the .dix file)
*4 sets of lexical selection rules
*:(now we have rules that solve 5 problems in total)
*3 items from contrastive grammar implemented in transfer rules
*:(now we have rules that implement 4 total items)

==Final evaluation==
* For the monolingual transducer:
** Updated precision and recall against the (updated) <code>eval.test</code> and <code>eval.gold</code> files
** Coverage over the <code>large</code> corpus:
TOP UNKNOWN WORDS:
2336 ^po/*po$
1275 ^che/*che$
448 ^i/*i$
387 ^norte/*norte$
377 ^The/*The$
353 ^of/*of$
297 ^poi/*poi$
269 ^del/*del$
241 ^the/*the$
235 ^da/*da$
215 ^ch/*ch$
211 ^Il/*Il$
205 ^chentza/*chentza$
200 ^br/*br$
199 ^Arbaree/*Arbaree$
197 ^della/*della$
192 ^stètiu/*stètiu$
165 ^ddoi/*ddoi$
154 ^B/*B$
145 ^Norte/*Norte$
coverage: 1648134 / 1822907 (~0.90412401729764601266)

TOP UNKNOWN WORDS:
12208 ^cun/*cun$
8207 ^prus/*prus$
5205 ^o/*o$
4218 ^comente/*comente$
4100 ^fintzas/*fintzas$
3068 ^pustis/*pustis$
2658 ^annos/*annos$
2623 ^totu/*totu$
2589 ^ma/*ma$
2417 ^sua/*sua$
2376 ^parte/*parte$
2336 ^po/*po$
2250 ^Sardigna/*Sardigna$
2233 ^intre/*intre$
2120 ^ca/*ca$
2070 ^tzitade/*tzitade$
1964 ^che/*che$
1888 ^ue/*ue$
1873 ^bidda/*bidda$
1739 ^manera/*manera$
coverage: 963208 / 1863589 (~0.51685645279082458632)

** The number of words in the <code>large</code> corpus,
** The number of stems in the transducer.

* For MT in the direction we developed (<code>srd-eng</code>):
** WER and PER over <code>longer</code> corpus:
-------------------------------------------------------
Number of words in reference: 315
Number of words in test: 341
Number of unknown words (marked with a star) in test: 35
Percentage of unknown words: 10.26 %

Results when removing unknown-word marks (stars)
-------------------------------------------------------
Edit distance: 246
Word error rate (WER): 78.10 %
Number of position-independent correct words: 118
Position-independent word error rate (PER): 70.79 %
** The proportion of stems translated correctly in the <code>longer</code> corpus.
118/341 = 34.6%
** Trimmed coverage over <code>longer</code> and <code>large</code> corpora.
** The number of tokens in <code>longer</code> and <code>large</code> corpora.
***<code>longer</code>: 341 tokens
***<code>large</code>: xxx tokens

==10 sentences glosses and outputs==
*Note: '''These are outputs at end of lexical transfer before lexical selection and other weeks' improvements were implemented'''
{| cellpadding=5
|Sardinian sentence || intended English translation || output of srd-eng-biltrans (lexical transfer) mode || output of srd-eng (full translation) mode
|-
|1) Su sardu est una limba antica. || Sardinian is an ancient language. || ^Su<det><def><m><sg>/The<det><def><m><sg>$ ^sardu<n><m><sg>/Sardinian<n><sg>$ ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$ ^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$^.<sent>/.<sent>$^.<sent>/.<sent>$
|| #The Sardinian #be #a language #ancient
|-
|2) Pro bider s'artìculu sighire custu culligamentu. || To read the article click on this link. || ^Pro<pr>/For<pr>/To<pr>$ ^bider<vblex><inf>/read<vblex><inf>$ ^su<det><def><mf><sg>/the<det><def><mf><sg>$ ^artìculu<n><m><sg>/article<n><sg>$ ^sighire<vblex><inf>/click<vblex><inf>$ ^custu<det><dem><m><sg>/this<det><m><sg>$ ^culligamentu<n><m><sg>/link<n><sg>$^.<sent>/.<sent>$^.<sent>/.<sent>$<m><sg>$ ^culligamentu<n><m><sg>/link<n><sg>$^.<sent>/.<sent>$^.<sent>/.<sent>$
|| For read #the article click #this link.
|-
|3) Su trenu sinke fit andande. || The train was leaving. || ^Su<det><def><m><sg>/The<det><def><m><sg>$ ^trenu<n><m><sg>/train<n><sg>$ ^sinke<cnjadv>/$ ^èssere<vbser><pii><p3><sg>/be<vbser><pii><p3><sg>$ ^andare<vblex><ger>/leave<vblex><ger>/go<vblex><ger>$^.<sent>/.<sent>$^.<sent>/.<sent>$

|| #The train #be leaving.
|-
|4) Su trenu at a arrivare a sas deke. || The train will arrive at ten. || ^Su<det><def><m><sg>/The<det><def><m><sg>$ ^trenu<n><m><sg>/train<n><sg>$ ^àere<vbhaver><pri><p3><sg>/have<vbhaver><pri><p3><sg>$ ^a<pr>/at<pr>/on<pr>/to<pr>$ ^arrivare<vblex><inf>/arrive<vblex><inf>$ ^a<pr>/at<pr>/on<pr>/to<pr>$ ^su<det><def><f><pl>/the<det><def><f><pl>$ ^deke<num><mf><sp>/ten<num><mf><sp>$^.<sent>/.<sent>$^.<sent>/.<sent>$
|| #The train #have at arrive at #the #ten.
|-
|5) Su trenu devet arrivare a sas deke. || The train should arrive at ten. || ^Su<det><def><m><sg>/The<det><def><m><sg>$ ^trenu<n><m><sg>/train<n><sg>$ ^dèvere<vblex><pri><p3><sg>/shall<vbmod><pri><p3><sg>$ ^arrivare<vblex><inf>/arrive<vblex><inf>$ ^a<pr>/at<pr>/on<pr>/to<pr>$ ^su<det><def><f><pl>/the<det><def><f><pl>$ ^deke<num><mf><sp>/ten<num><mf><sp>$^.<sent>/.<sent>$^.<sent>/.<sent>$
|| #The train #shall arrive at #the #ten.
|-
|6) T'appo natu ki su trenu devíat arrivare a sas deke. || I told you that the train would arrive at ten. || ^Ti<prn><pro><p2><mf><sg>/You<prn><pro><p2><mf><sg>$ ^àere<vbhaver><pri><p1><sg>/have<vbhaver><pri><p1><sg>$ ^nàrrere<vblex><pp><m><sg>/tell<vblex><pp><m><sg>$ ^chi<cnjsub>/that<cnjsub>$ ^su<det><def><m><sg>/the<det><def><m><sg>$ ^trenu<n><m><sg>/train<n><sg>$ ^dèvere<vblex><pii><p3><sg>/shall<vbmod><pii><p3><sg>$ ^arrivare<vblex><inf>/arrive<vblex><inf>$ ^a<pr>/at<pr>/on<pr>/to<pr>$ ^su<det><def><f><pl>/the<det><def><f><pl>$ ^deke<num><mf><sp>/ten<num><mf><sp>$^.<sent>/.<sent>$^.<sent>/.<sent>$
|| #You #have #tell that #the train #shall arrive at #the #ten.
|-
|7) No'isco si at a pròere cras. || I do not know if it will rain tomorrow. || ^No<adv>/Not<adv>$'^iscoare<vblex><pri><p1><sg>/know<vblex><pri><p1><sg>$ ^si<cnjsub>/if<cnjsub>$ ^àere<vbhaver><pri><p3><sg>/have<vbhaver><pri><p3><sg>$ ^a<pr>/at<pr>/on<pr>/to<pr>$ ^pròere<vblex><inf>/rain<vblex><inf>$ ^cras<adv>/tomorrow<adv>$^.<sent>/.<sent>$
|| Not'#know if #have at rain tomorrow

|-
|8) Una de sas berbekes est maláida. || One of the sheep is sick. || ^Unu<num><f><sp>/One<num><f><sp>$ ^de<pr>/to<pr>/of<pr>$ ^su<det><def><f><pl>/the<det><def><f><pl>$ ^berbeke<n><f><pl>/sheep<n><pl>$ ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$ ^malàidu<adj><f><sg>/sick<adj><f><sg>$^.<sent>/.<sent>$
|| #One to #the sheep #be #sick

|-
|9) Appo pèrditu duos de sos libros meos. || I have lost two of my books. || ^Àere<vbhaver><pri><p1><sg>/Have<vbhaver><pri><p1><sg>$ ^pèrdere<vblex><pp><m><sg>/lose<vblex><pp><m><sg>$ ^duos<num><m><sp>/two<num><m><sp>$ ^de<pr>/to<pr>/of<pr>$ ^su<det><def><m><pl>/the<det><def><m><pl>$ ^libru<n><m><pl>/book<n><pl>$ ^meu<prn><pos><m><pl>/my<prn><pos><m><pl>$^.<sent>/.<sent>$

|| #Have #lose #two to #the books #my

|-
|10) M'an natu ki su trenu devíat arrivare a sas nove. || They told me that the train was supposed to arrive at nine. || ^Mi<prn><pro><p1><mf><sg>/I<prn><pro><p1><mf><sg>$ ^àere<vbhaver><pri><p3><pl>/have<vbhaver><pri><p3><pl>$ ^nàrrere<vblex><pp><m><sg>/tell<vblex><pp><m><sg>$ ^chi<cnjsub>/that<cnjsub>$ ^su<det><def><m><sg>/the<det><def><m><sg>$ ^trenu<n><m><sg>/train<n><sg>$ ^dèvere<vblex><pii><p3><sg>/shall<vbmod><pii><p3><sg>$ ^arrivare<vblex><inf>/arrive<vblex><inf>$ ^a<pr>/at<pr>/on<pr>/to<pr>$ ^su<det><def><f><pl>/the<det><def><f><pl>$ ^nove<num><mf><sp>/nine<num><mf><sp>$^.<sent>/.<sent>$
|| #I #have #tell that #the train #shall arrive at #the #nine
|
|}

==expanding lexicon==

{| cellpadding=5
|medas || many || <adj>
|-https://wikis.swarthmore.edu/ling073/index.php?title=Sardinian_and_English&action=edit
|piseddas || girls || <n><pl>
|-
|sun || they are || <v>
|-
|bennidas || to come (home) || <v><pp><fpl>
|-
|balladu || to dance || <v><pp>
|-
|cantaiat || to sing || <v><sg3>
|-
|sos/sa || the || <det>
|-
|piattos || plates || <n><pl>
|-
|mesa || table || <n><sg>
|-
|bi/b' || N/A || <cl>
|-
|problemas || problems || <n><pl>
|-
|unu || one/a || <adj>/<det>
|-
|ube || where || <adv>
|-
|mortu || dead || <v><pp>
|-
|sordatos || soldiers || <n><pl>
|-
|tenimus || we have || <v><pl1>
|-
|frores || flowers || <n><pl>
|-
|keret || to be necessary || <v><sg3>
|-
|mancat || to be missing || <v><sg3>
|-
|ovos || eggs || <n><pl>
|-
|danca || meadow || <n>
|-
|ortu || orchard || <n>
|-
|frade || brother || <n>
|-
|fizza || daughter || <n>
|-
|re || king || <n>
|-
|ora || hour || <n>
|-
|subra || above/on || <prep>
|-
|a || to/at || <prep>
|-
|cumintzos || origins || <n><pl>
|-
|e || and || <conj>
|-
|andamentu || evolution || <n>
|-
|istòricu || historical || <adj>
|-
|de || of/to || <prep>
|-
|sa || the || <det>
|-
|poesia || poetry || <n>
|-
|a bolu || improvised || <adj> (a bolu = improvised, on the fly)
|-
|in || in || <prep>
|-
|sardu || Sardinian || <n>
|-
|logudoresu || Logudorese || <adj>
|-
|non || not || <adv>
|-
|ischit || known || <v><pp>
|-
|meda || much || <adv>
|-
|custu || this || <det><prox>
|-
|artìculu || article || <n>
|-
|chircat || tries || <v><sg3>
|-
|bogare || to bring out || <v>
|-
|pizu || surface || <n> (bogare a pizu = to shed light on, to bring to the surface; see complicated translations of bogare: [http://vocabolariocasu.isresardegna.it/index.php?key=b&int=0&lemmi=cerca&codice=b1264000 here])
|-
|ammentos || memories || <n><pl>
|-
|ammentu || memory || <n>
|-
|ammentare || to remember || <v>
|-
|documentados || documented || <adj>
|-
|si || [null] || <> -- reflexive
|-
|primas || first || <adj>
|-
|disputas || competitions || <n><pl>
|-
|primas || first || <adj>
|-
|tra || between || <prep>
|-
|poetes || poets || <n><pl>
|-
|cale || which || <prn><rel>
|-
|esserent || were || <v> past imperfect 3rd person plural
|-
|règulas || rules, modalities || <n><pl>
|-
|su || the || <det>
|-
|cunfruntu || confrontation || <n>
|-
|sende || being || <v><ger>
|-
|una || a/one || <art>/<adj>
|-
|chirca || research || <n>
|-
|andera || ongoing/progressive || <adj>
|-
|testu || text || <n>
|-
|diat || [null] || <subj><sg3>
|-
|poder || to be able to || <v><inf>
|-
|aer || to have || <v><inf> (also hàere or àere)
|-
|mudonzos || modifications || <n><pl>
|-
|mudonzos || modifications || <n><pl>
|-
|novas || new || <adj><pl>
|-
|noas || data || <n><pl>
|-
|Pro || to || <prep> <-- keep this in mind for lexical selection (to)
|-
|bider || to read || <v><inf>
|-
|artìculu || article || <n>
|-
|sighire || click on || <v><inf>
|-
|intrare || enter || <v><inf>
|-
|desizadu || desired || <adj>
|-
|trenu || train || <n>
|-
|sinke || [null] || <foc>
|-
|fit || was || <v><imp><sg3>
|-
|andande || leaving || <v><ger>
|-
|at || it will || <>
|-
|sas || the || <det>
|-
|deke || ten || <n>
|-
|devet || should || <adv>
|-
|deke || ten || <adj>
|-
|appo || I have || <v><sg1>
|-
|natu || told || <v><pp>
|-
|próere || to rain || <v><inf>
|-
|arrivare || to arrive || <v><inf>
|-
|isco || I know || <v><sg1>
|-
|si || if || <conj>
|-
|ki || that || <conj>
|-
|cras || tomorrow || <adv>
|-
|meos || my || <pos>
|-
|andatos || gone || <adj><pl>
|
|}

===glosses===

Cando so arrivatu a s'istazione, su trenu sink'andaiat

'when I arrived at the station, the train was leaving'

Su trenu sinke fit andande

'The train was leaving"

Su trenu at a arrivare a sas deke

'The train will arrive at ten o'clock'

Su trenu devet arrivare a sas deke

'The train is supposed to arrive at ten o'clock'

T'appo natu ki su trenu diat arrivare a sas deke

'I told you that the train would arrive at ten o'clock'

M'an natu ki su trenu devíat arrivare a sas nove

'They told me that the train was supposed to arrive at nine'

At a próere cras

'It will rain tomorrow'

Devet próere cras

'it is supposed to rain tomorrow'

At a próere cras? Si emmo abbarramus in domo, ma su nono andamus a mare

'Will it rain tomorrow? If so we shall stay at homr, buy if not we will go to the sea'

No'isco si at a próere cras

'I do to know whether it will rain tomorrow'

Una de sas berbekes est maláida

'one of the sheep is sick'

Appo pèrditu duos de sos libros meos

'I have lost two of my books'

Metas de custas pitzinnas sun galanas

'Many of these girls are pretty'

Una pitzinna meta bella

'a very beautiful girl'

Cussas duas bravas pitzinnas

'those two good girls'

unu better cane bellu

'a huge beautiful dog'

un'átteru bette cane

'another huge dog'

Sun andatos a Frantza

'they went to France'

Est ghiratu dae Corsica

'He returned from Corsica'

Connnosco bene sa Frantza

"i know France well'

Custu libru est iscrittu in tedescu

'This book is written in German'

Cussus paráula venit dae su catalanu

'This word comes from Catalan'

Su sardu est una limba antica

'Sardinian is an ancient language'

Appo mandicatu casu

'I ate cheese'

Laura est toddende frores

'Laura is picking flowers'

De frores non nd'appo tódditu

'I did not pick any flowers'

No'amus comporatu pane

'We did not buy bread'

Mandico sa pasta kin casu

'I ate pasta with cheese'

Tres sórrikes an mandicatu tottu su casu

'Three mice ate all the cheese'

semus ponnende vinu in ampullas

'We are putting wine in bottles'

lettu meu esr

'It is my bed'

No'appo lessu libru perunu

'i did not read any book'

Sos k'an furatu si dinari at a èssere punitos

'The people who stole the money will be punished'

Appo invitat sos de Juanne

'I invited Jon's family'

Cussa pinna est sa mea

'That pen is mine'

Cudda mákkina est sa de Juanne

'That car is John's'

Custa ricca at datu mili francos a su vetzu

'This rich woman gave a thousand lira to the old man'

Su guvernu devíat dare ua pensione a dondzi vetzu

'The government should give a pension to every old person'

==External Resources==

*Github repository for [https://github.com/apertium/apertium-srd Sardinian transducer] (and our [https://github.swarthmore.edu/Ling073-sp23/ling073-srd clone])
*Github repository for [https://github.com/apertium/apertium-eng English transducer]
*[https://www.limbasardasudsardigna.it/sar/images/Documenti/Didatica_e_Ainas/Ditzion%C3%A0riu%20Universale%20Rubattu.pdf Dictionary pdf]
*[http://ditzionariu.sardegnacultura.it/it/ Online official dictionary]
*[https://it.glosbe.com/sc/it Web-based machine translator]
*[http://vocabolariocasu.isresardegna.it/index.php?key=a&int=0&lemmi=cerca Sardinian-Italian web-based dictionary]
*[http://www.sardegnadigitallibrary.it/mmt/fullsize/2009050512495700047.pdf 1931 pdf with select translations]
*[https://onlinelibrary.wiley.com/doi/epdf/10.1111/j.0079-1636.2004.00130.x Definiteness effects: evidence from Sardinian]
*[https://www.icongrouponline.com/en/Detail/dictionary/049783698X/Webster%27s+Sardinian+-+English+Thesaurus+Dictionary: Webster's Sardinian English Thesaurus Dictionary]
*[https://www.academia.edu/15320922/Dizionario_della_lingua_Sarda_Vol_2 Italian-Sardinian Dictionary]
*[https://archive.org/details/vocabolariosardo00spanuoft/page/n361/mode/2up Old but extensive Sardo-Italian and vice versa dictionary]
*[https://limbasardasudsardigna.it/sar/images/Documenti/Didatica_e_Ainas/Vocabolariu_Sardu_Italianu_Spano.pdf nice Sardo-Italiano dictionary pdf]
*[http://www.fontesarda.it/sr/sr0045.htm Conjugations of "to have" in Sardinian]
*[https://sinnainotizie.com/2015/03/07/lezioni-di-grammatica-sardo-campidanese-undicesima-lezione-su-verbu-ai-aere/ Whole Sardinian grammar page about conjugations of to have all written in Sardinian language!]
*Sardinian grammar:[https://www.limbasardasudsardigna.it/sar/images/Documenti/Didatica_e_Ainas/grammatiga_sardo%20campidanese%20A.LEPORI.pdf pdf]
[[Category:Sp23_TranslationPairs]],[[Category:Sardinian]],[[Category:English]]

Sardinian and English

2023-05-05T18:10:48Z

Rorlija1: /* Final evaluation */

=Resources for Machine Translation from Sardinian to English=

==Developed Resources==
*[https://github.swarthmore.edu/Ling073-sp23/ling073-srd-eng-corpus Parallel corpus git repo].
*:Lines 1-8 from [http://maxia-mail.doomby.com/ this website].
*[https://github.swarthmore.edu/Ling073-sp23/ling073-srd-eng Git repo for language pair]
*[https://github.swarthmore.edu/Ling073-sp23/ling073-srd Git repo for Sardinian]
*[https://github.com/apertium/apertium-eng Forked git repo for English]
*[https://wikis.swarthmore.edu/ling073/Sardinian_and_English/Lexical_selection#srd_.E2.86.92_eng Lexical selection wiki]
*[https://wikis.swarthmore.edu/ling073/Sardinian_and_English/Contrastive_Grammar#Differences_in_parse_and_corresponding_examples Contrastive grammar wiki]
*[https://wikis.swarthmore.edu/ling073/Sardinian_and_English/Structural_transfer Structural transfer wiki]

==srd → eng evaluation==
*coverage of monolingual Sardinian transducer on srd.sentences.txt:
Number of tokenised words in the corpus: 262
Coverage: 94.66%
*coverage of bilingual transducer on srd.sentences
Number of tokenised words in the corpus: 266
Coverage: 85.71%

==Additions for polished RBMT system==
*Over 100 new stems to bilingual dictionary
*:(now we have 172 total entries in the .dix file)
*4 sets of lexical selection rules
*:(now we have rules that solve 5 problems in total)
*3 items from contrastive grammar implemented in transfer rules
*:(now we have rules that implement 4 total items)

==Final evaluation==
* For the monolingual transducer:
** Updated precision and recall against the (updated) <code>eval.test</code> and <code>eval.gold</code> files
** Coverage over the <code>large</code> corpus:
** The number of words in the <code>large</code> corpus,
** The number of stems in the transducer.

* For MT in the direction we developed (<code>srd-eng</code>):
** WER and PER over <code>longer</code> corpus:
-------------------------------------------------------
Number of words in reference: 315
Number of words in test: 341
Number of unknown words (marked with a star) in test: 35
Percentage of unknown words: 10.26 %

Results when removing unknown-word marks (stars)
-------------------------------------------------------
Edit distance: 246
Word error rate (WER): 78.10 %
Number of position-independent correct words: 118
Position-independent word error rate (PER): 70.79 %
** The proportion of stems translated correctly in the <code>longer</code> corpus.
118/341 = 34.6%
** Trimmed coverage over <code>longer</code> and <code>large</code> corpora.
** The number of tokens in <code>longer</code> and <code>large</code> corpora.
***<code>longer</code>: 341 tokens
***<code>large</code>: xxx tokens

==10 sentences glosses and outputs==
*Note: '''These are outputs at end of lexical transfer before lexical selection and other weeks' improvements were implemented'''
{| cellpadding=5
|Sardinian sentence || intended English translation || output of srd-eng-biltrans (lexical transfer) mode || output of srd-eng (full translation) mode
|-
|1) Su sardu est una limba antica. || Sardinian is an ancient language. || ^Su<det><def><m><sg>/The<det><def><m><sg>$ ^sardu<n><m><sg>/Sardinian<n><sg>$ ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$ ^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$^.<sent>/.<sent>$^.<sent>/.<sent>$
|| #The Sardinian #be #a language #ancient
|-
|2) Pro bider s'artìculu sighire custu culligamentu. || To read the article click on this link. || ^Pro<pr>/For<pr>/To<pr>$ ^bider<vblex><inf>/read<vblex><inf>$ ^su<det><def><mf><sg>/the<det><def><mf><sg>$ ^artìculu<n><m><sg>/article<n><sg>$ ^sighire<vblex><inf>/click<vblex><inf>$ ^custu<det><dem><m><sg>/this<det><m><sg>$ ^culligamentu<n><m><sg>/link<n><sg>$^.<sent>/.<sent>$^.<sent>/.<sent>$<m><sg>$ ^culligamentu<n><m><sg>/link<n><sg>$^.<sent>/.<sent>$^.<sent>/.<sent>$
|| For read #the article click #this link.
|-
|3) Su trenu sinke fit andande. || The train was leaving. || ^Su<det><def><m><sg>/The<det><def><m><sg>$ ^trenu<n><m><sg>/train<n><sg>$ ^sinke<cnjadv>/$ ^èssere<vbser><pii><p3><sg>/be<vbser><pii><p3><sg>$ ^andare<vblex><ger>/leave<vblex><ger>/go<vblex><ger>$^.<sent>/.<sent>$^.<sent>/.<sent>$

|| #The train #be leaving.
|-
|4) Su trenu at a arrivare a sas deke. || The train will arrive at ten. || ^Su<det><def><m><sg>/The<det><def><m><sg>$ ^trenu<n><m><sg>/train<n><sg>$ ^àere<vbhaver><pri><p3><sg>/have<vbhaver><pri><p3><sg>$ ^a<pr>/at<pr>/on<pr>/to<pr>$ ^arrivare<vblex><inf>/arrive<vblex><inf>$ ^a<pr>/at<pr>/on<pr>/to<pr>$ ^su<det><def><f><pl>/the<det><def><f><pl>$ ^deke<num><mf><sp>/ten<num><mf><sp>$^.<sent>/.<sent>$^.<sent>/.<sent>$
|| #The train #have at arrive at #the #ten.
|-
|5) Su trenu devet arrivare a sas deke. || The train should arrive at ten. || ^Su<det><def><m><sg>/The<det><def><m><sg>$ ^trenu<n><m><sg>/train<n><sg>$ ^dèvere<vblex><pri><p3><sg>/shall<vbmod><pri><p3><sg>$ ^arrivare<vblex><inf>/arrive<vblex><inf>$ ^a<pr>/at<pr>/on<pr>/to<pr>$ ^su<det><def><f><pl>/the<det><def><f><pl>$ ^deke<num><mf><sp>/ten<num><mf><sp>$^.<sent>/.<sent>$^.<sent>/.<sent>$
|| #The train #shall arrive at #the #ten.
|-
|6) T'appo natu ki su trenu devíat arrivare a sas deke. || I told you that the train would arrive at ten. || ^Ti<prn><pro><p2><mf><sg>/You<prn><pro><p2><mf><sg>$ ^àere<vbhaver><pri><p1><sg>/have<vbhaver><pri><p1><sg>$ ^nàrrere<vblex><pp><m><sg>/tell<vblex><pp><m><sg>$ ^chi<cnjsub>/that<cnjsub>$ ^su<det><def><m><sg>/the<det><def><m><sg>$ ^trenu<n><m><sg>/train<n><sg>$ ^dèvere<vblex><pii><p3><sg>/shall<vbmod><pii><p3><sg>$ ^arrivare<vblex><inf>/arrive<vblex><inf>$ ^a<pr>/at<pr>/on<pr>/to<pr>$ ^su<det><def><f><pl>/the<det><def><f><pl>$ ^deke<num><mf><sp>/ten<num><mf><sp>$^.<sent>/.<sent>$^.<sent>/.<sent>$
|| #You #have #tell that #the train #shall arrive at #the #ten.
|-
|7) No'isco si at a pròere cras. || I do not know if it will rain tomorrow. || ^No<adv>/Not<adv>$'^iscoare<vblex><pri><p1><sg>/know<vblex><pri><p1><sg>$ ^si<cnjsub>/if<cnjsub>$ ^àere<vbhaver><pri><p3><sg>/have<vbhaver><pri><p3><sg>$ ^a<pr>/at<pr>/on<pr>/to<pr>$ ^pròere<vblex><inf>/rain<vblex><inf>$ ^cras<adv>/tomorrow<adv>$^.<sent>/.<sent>$
|| Not'#know if #have at rain tomorrow

|-
|8) Una de sas berbekes est maláida. || One of the sheep is sick. || ^Unu<num><f><sp>/One<num><f><sp>$ ^de<pr>/to<pr>/of<pr>$ ^su<det><def><f><pl>/the<det><def><f><pl>$ ^berbeke<n><f><pl>/sheep<n><pl>$ ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$ ^malàidu<adj><f><sg>/sick<adj><f><sg>$^.<sent>/.<sent>$
|| #One to #the sheep #be #sick

|-
|9) Appo pèrditu duos de sos libros meos. || I have lost two of my books. || ^Àere<vbhaver><pri><p1><sg>/Have<vbhaver><pri><p1><sg>$ ^pèrdere<vblex><pp><m><sg>/lose<vblex><pp><m><sg>$ ^duos<num><m><sp>/two<num><m><sp>$ ^de<pr>/to<pr>/of<pr>$ ^su<det><def><m><pl>/the<det><def><m><pl>$ ^libru<n><m><pl>/book<n><pl>$ ^meu<prn><pos><m><pl>/my<prn><pos><m><pl>$^.<sent>/.<sent>$

|| #Have #lose #two to #the books #my

|-
|10) M'an natu ki su trenu devíat arrivare a sas nove. || They told me that the train was supposed to arrive at nine. || ^Mi<prn><pro><p1><mf><sg>/I<prn><pro><p1><mf><sg>$ ^àere<vbhaver><pri><p3><pl>/have<vbhaver><pri><p3><pl>$ ^nàrrere<vblex><pp><m><sg>/tell<vblex><pp><m><sg>$ ^chi<cnjsub>/that<cnjsub>$ ^su<det><def><m><sg>/the<det><def><m><sg>$ ^trenu<n><m><sg>/train<n><sg>$ ^dèvere<vblex><pii><p3><sg>/shall<vbmod><pii><p3><sg>$ ^arrivare<vblex><inf>/arrive<vblex><inf>$ ^a<pr>/at<pr>/on<pr>/to<pr>$ ^su<det><def><f><pl>/the<det><def><f><pl>$ ^nove<num><mf><sp>/nine<num><mf><sp>$^.<sent>/.<sent>$
|| #I #have #tell that #the train #shall arrive at #the #nine
|
|}

==expanding lexicon==

{| cellpadding=5
|medas || many || <adj>
|-https://wikis.swarthmore.edu/ling073/index.php?title=Sardinian_and_English&action=edit
|piseddas || girls || <n><pl>
|-
|sun || they are || <v>
|-
|bennidas || to come (home) || <v><pp><fpl>
|-
|balladu || to dance || <v><pp>
|-
|cantaiat || to sing || <v><sg3>
|-
|sos/sa || the || <det>
|-
|piattos || plates || <n><pl>
|-
|mesa || table || <n><sg>
|-
|bi/b' || N/A || <cl>
|-
|problemas || problems || <n><pl>
|-
|unu || one/a || <adj>/<det>
|-
|ube || where || <adv>
|-
|mortu || dead || <v><pp>
|-
|sordatos || soldiers || <n><pl>
|-
|tenimus || we have || <v><pl1>
|-
|frores || flowers || <n><pl>
|-
|keret || to be necessary || <v><sg3>
|-
|mancat || to be missing || <v><sg3>
|-
|ovos || eggs || <n><pl>
|-
|danca || meadow || <n>
|-
|ortu || orchard || <n>
|-
|frade || brother || <n>
|-
|fizza || daughter || <n>
|-
|re || king || <n>
|-
|ora || hour || <n>
|-
|subra || above/on || <prep>
|-
|a || to/at || <prep>
|-
|cumintzos || origins || <n><pl>
|-
|e || and || <conj>
|-
|andamentu || evolution || <n>
|-
|istòricu || historical || <adj>
|-
|de || of/to || <prep>
|-
|sa || the || <det>
|-
|poesia || poetry || <n>
|-
|a bolu || improvised || <adj> (a bolu = improvised, on the fly)
|-
|in || in || <prep>
|-
|sardu || Sardinian || <n>
|-
|logudoresu || Logudorese || <adj>
|-
|non || not || <adv>
|-
|ischit || known || <v><pp>
|-
|meda || much || <adv>
|-
|custu || this || <det><prox>
|-
|artìculu || article || <n>
|-
|chircat || tries || <v><sg3>
|-
|bogare || to bring out || <v>
|-
|pizu || surface || <n> (bogare a pizu = to shed light on, to bring to the surface; see complicated translations of bogare: [http://vocabolariocasu.isresardegna.it/index.php?key=b&int=0&lemmi=cerca&codice=b1264000 here])
|-
|ammentos || memories || <n><pl>
|-
|ammentu || memory || <n>
|-
|ammentare || to remember || <v>
|-
|documentados || documented || <adj>
|-
|si || [null] || <> -- reflexive
|-
|primas || first || <adj>
|-
|disputas || competitions || <n><pl>
|-
|primas || first || <adj>
|-
|tra || between || <prep>
|-
|poetes || poets || <n><pl>
|-
|cale || which || <prn><rel>
|-
|esserent || were || <v> past imperfect 3rd person plural
|-
|règulas || rules, modalities || <n><pl>
|-
|su || the || <det>
|-
|cunfruntu || confrontation || <n>
|-
|sende || being || <v><ger>
|-
|una || a/one || <art>/<adj>
|-
|chirca || research || <n>
|-
|andera || ongoing/progressive || <adj>
|-
|testu || text || <n>
|-
|diat || [null] || <subj><sg3>
|-
|poder || to be able to || <v><inf>
|-
|aer || to have || <v><inf> (also hàere or àere)
|-
|mudonzos || modifications || <n><pl>
|-
|mudonzos || modifications || <n><pl>
|-
|novas || new || <adj><pl>
|-
|noas || data || <n><pl>
|-
|Pro || to || <prep> <-- keep this in mind for lexical selection (to)
|-
|bider || to read || <v><inf>
|-
|artìculu || article || <n>
|-
|sighire || click on || <v><inf>
|-
|intrare || enter || <v><inf>
|-
|desizadu || desired || <adj>
|-
|trenu || train || <n>
|-
|sinke || [null] || <foc>
|-
|fit || was || <v><imp><sg3>
|-
|andande || leaving || <v><ger>
|-
|at || it will || <>
|-
|sas || the || <det>
|-
|deke || ten || <n>
|-
|devet || should || <adv>
|-
|deke || ten || <adj>
|-
|appo || I have || <v><sg1>
|-
|natu || told || <v><pp>
|-
|próere || to rain || <v><inf>
|-
|arrivare || to arrive || <v><inf>
|-
|isco || I know || <v><sg1>
|-
|si || if || <conj>
|-
|ki || that || <conj>
|-
|cras || tomorrow || <adv>
|-
|meos || my || <pos>
|-
|andatos || gone || <adj><pl>
|
|}

===glosses===

Cando so arrivatu a s'istazione, su trenu sink'andaiat

'when I arrived at the station, the train was leaving'

Su trenu sinke fit andande

'The train was leaving"

Su trenu at a arrivare a sas deke

'The train will arrive at ten o'clock'

Su trenu devet arrivare a sas deke

'The train is supposed to arrive at ten o'clock'

T'appo natu ki su trenu diat arrivare a sas deke

'I told you that the train would arrive at ten o'clock'

M'an natu ki su trenu devíat arrivare a sas nove

'They told me that the train was supposed to arrive at nine'

At a próere cras

'It will rain tomorrow'

Devet próere cras

'it is supposed to rain tomorrow'

At a próere cras? Si emmo abbarramus in domo, ma su nono andamus a mare

'Will it rain tomorrow? If so we shall stay at homr, buy if not we will go to the sea'

No'isco si at a próere cras

'I do to know whether it will rain tomorrow'

Una de sas berbekes est maláida

'one of the sheep is sick'

Appo pèrditu duos de sos libros meos

'I have lost two of my books'

Metas de custas pitzinnas sun galanas

'Many of these girls are pretty'

Una pitzinna meta bella

'a very beautiful girl'

Cussas duas bravas pitzinnas

'those two good girls'

unu better cane bellu

'a huge beautiful dog'

un'átteru bette cane

'another huge dog'

Sun andatos a Frantza

'they went to France'

Est ghiratu dae Corsica

'He returned from Corsica'

Connnosco bene sa Frantza

"i know France well'

Custu libru est iscrittu in tedescu

'This book is written in German'

Cussus paráula venit dae su catalanu

'This word comes from Catalan'

Su sardu est una limba antica

'Sardinian is an ancient language'

Appo mandicatu casu

'I ate cheese'

Laura est toddende frores

'Laura is picking flowers'

De frores non nd'appo tódditu

'I did not pick any flowers'

No'amus comporatu pane

'We did not buy bread'

Mandico sa pasta kin casu

'I ate pasta with cheese'

Tres sórrikes an mandicatu tottu su casu

'Three mice ate all the cheese'

semus ponnende vinu in ampullas

'We are putting wine in bottles'

lettu meu esr

'It is my bed'

No'appo lessu libru perunu

'i did not read any book'

Sos k'an furatu si dinari at a èssere punitos

'The people who stole the money will be punished'

Appo invitat sos de Juanne

'I invited Jon's family'

Cussa pinna est sa mea

'That pen is mine'

Cudda mákkina est sa de Juanne

'That car is John's'

Custa ricca at datu mili francos a su vetzu

'This rich woman gave a thousand lira to the old man'

Su guvernu devíat dare ua pensione a dondzi vetzu

'The government should give a pension to every old person'

==External Resources==

*Github repository for [https://github.com/apertium/apertium-srd Sardinian transducer] (and our [https://github.swarthmore.edu/Ling073-sp23/ling073-srd clone])
*Github repository for [https://github.com/apertium/apertium-eng English transducer]
*[https://www.limbasardasudsardigna.it/sar/images/Documenti/Didatica_e_Ainas/Ditzion%C3%A0riu%20Universale%20Rubattu.pdf Dictionary pdf]
*[http://ditzionariu.sardegnacultura.it/it/ Online official dictionary]
*[https://it.glosbe.com/sc/it Web-based machine translator]
*[http://vocabolariocasu.isresardegna.it/index.php?key=a&int=0&lemmi=cerca Sardinian-Italian web-based dictionary]
*[http://www.sardegnadigitallibrary.it/mmt/fullsize/2009050512495700047.pdf 1931 pdf with select translations]
*[https://onlinelibrary.wiley.com/doi/epdf/10.1111/j.0079-1636.2004.00130.x Definiteness effects: evidence from Sardinian]
*[https://www.icongrouponline.com/en/Detail/dictionary/049783698X/Webster%27s+Sardinian+-+English+Thesaurus+Dictionary: Webster's Sardinian English Thesaurus Dictionary]
*[https://www.academia.edu/15320922/Dizionario_della_lingua_Sarda_Vol_2 Italian-Sardinian Dictionary]
*[https://archive.org/details/vocabolariosardo00spanuoft/page/n361/mode/2up Old but extensive Sardo-Italian and vice versa dictionary]
*[https://limbasardasudsardigna.it/sar/images/Documenti/Didatica_e_Ainas/Vocabolariu_Sardu_Italianu_Spano.pdf nice Sardo-Italiano dictionary pdf]
*[http://www.fontesarda.it/sr/sr0045.htm Conjugations of "to have" in Sardinian]
*[https://sinnainotizie.com/2015/03/07/lezioni-di-grammatica-sardo-campidanese-undicesima-lezione-su-verbu-ai-aere/ Whole Sardinian grammar page about conjugations of to have all written in Sardinian language!]
*Sardinian grammar:[https://www.limbasardasudsardigna.it/sar/images/Documenti/Didatica_e_Ainas/grammatiga_sardo%20campidanese%20A.LEPORI.pdf pdf]
[[Category:Sp23_TranslationPairs]],[[Category:Sardinian]],[[Category:English]]

Sardinian and English

2023-05-04T18:04:41Z

Rorlija1: /* Final evaluation */

=Resources for Machine Translation from Sardinian to English=

==Developed Resources==
*[https://github.swarthmore.edu/Ling073-sp23/ling073-srd-eng-corpus Parallel corpus git repo].
*:Lines 1-8 from [http://maxia-mail.doomby.com/ this website].
*[https://github.swarthmore.edu/Ling073-sp23/ling073-srd-eng Git repo for language pair]
*[https://github.swarthmore.edu/Ling073-sp23/ling073-srd Git repo for Sardinian]
*[https://github.com/apertium/apertium-eng Forked git repo for English]
*[https://wikis.swarthmore.edu/ling073/Sardinian_and_English/Lexical_selection#srd_.E2.86.92_eng Lexical selection wiki]
*[https://wikis.swarthmore.edu/ling073/Sardinian_and_English/Contrastive_Grammar#Differences_in_parse_and_corresponding_examples Contrastive grammar wiki]
*[https://wikis.swarthmore.edu/ling073/Sardinian_and_English/Structural_transfer Structural transfer wiki]

==srd → eng evaluation==
*coverage of monolingual Sardinian transducer on srd.sentences.txt:
Number of tokenised words in the corpus: 262
Coverage: 94.66%
*coverage of bilingual transducer on srd.sentences
Number of tokenised words in the corpus: 266
Coverage: 85.71%

==Additions for polished RBMT system==
*Over 100 new stems to bilingual dictionary
*:(now we have 172 total entries in the .dix file)
*4 sets of lexical selection rules
*:(now we have rules that solve 5 problems in total)
*3 items from contrastive grammar implemented in transfer rules
*:(now we have rules that implement 4 total items)

==Final evaluation==
* For the monolingual transducer:
** Updated precision and recall against the (updated) <code>eval.test</code> and <code>eval.gold</code> files
** Coverage over the <code>large</code> corpus:
** The number of words in the <code>large</code> corpus,
** The number of stems in the transducer.

* For MT in the direction we developed (<code>srd-eng</code>):
** WER and PER over <code>longer</code> corpus:
-------------------------------------------------------
Number of words in reference: 315
Number of words in test: 341
Number of unknown words (marked with a star) in test: 35
Percentage of unknown words: 10.26 %

Results when removing unknown-word marks (stars)
-------------------------------------------------------
Edit distance: 246
Word error rate (WER): 78.10 %
Number of position-independent correct words: 118
Position-independent word error rate (PER): 70.79 %
** The proportion of stems translated correctly in the <code>longer</code> corpus.
118/346 = 34.6%
** Trimmed coverage over <code>longer</code> and <code>large</code> corpora.
** The number of tokens in <code>longer</code> and <code>large</code> corpora.

==10 sentences glosses and outputs==
*Note: '''These are outputs at end of lexical transfer before lexical selection and other weeks' improvements were implemented'''
{| cellpadding=5
|Sardinian sentence || intended English translation || output of srd-eng-biltrans (lexical transfer) mode || output of srd-eng (full translation) mode
|-
|1) Su sardu est una limba antica. || Sardinian is an ancient language. || ^Su<det><def><m><sg>/The<det><def><m><sg>$ ^sardu<n><m><sg>/Sardinian<n><sg>$ ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$ ^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$^.<sent>/.<sent>$^.<sent>/.<sent>$
|| #The Sardinian #be #a language #ancient
|-
|2) Pro bider s'artìculu sighire custu culligamentu. || To read the article click on this link. || ^Pro<pr>/For<pr>/To<pr>$ ^bider<vblex><inf>/read<vblex><inf>$ ^su<det><def><mf><sg>/the<det><def><mf><sg>$ ^artìculu<n><m><sg>/article<n><sg>$ ^sighire<vblex><inf>/click<vblex><inf>$ ^custu<det><dem><m><sg>/this<det><m><sg>$ ^culligamentu<n><m><sg>/link<n><sg>$^.<sent>/.<sent>$^.<sent>/.<sent>$<m><sg>$ ^culligamentu<n><m><sg>/link<n><sg>$^.<sent>/.<sent>$^.<sent>/.<sent>$
|| For read #the article click #this link.
|-
|3) Su trenu sinke fit andande. || The train was leaving. || ^Su<det><def><m><sg>/The<det><def><m><sg>$ ^trenu<n><m><sg>/train<n><sg>$ ^sinke<cnjadv>/$ ^èssere<vbser><pii><p3><sg>/be<vbser><pii><p3><sg>$ ^andare<vblex><ger>/leave<vblex><ger>/go<vblex><ger>$^.<sent>/.<sent>$^.<sent>/.<sent>$

|| #The train #be leaving.
|-
|4) Su trenu at a arrivare a sas deke. || The train will arrive at ten. || ^Su<det><def><m><sg>/The<det><def><m><sg>$ ^trenu<n><m><sg>/train<n><sg>$ ^àere<vbhaver><pri><p3><sg>/have<vbhaver><pri><p3><sg>$ ^a<pr>/at<pr>/on<pr>/to<pr>$ ^arrivare<vblex><inf>/arrive<vblex><inf>$ ^a<pr>/at<pr>/on<pr>/to<pr>$ ^su<det><def><f><pl>/the<det><def><f><pl>$ ^deke<num><mf><sp>/ten<num><mf><sp>$^.<sent>/.<sent>$^.<sent>/.<sent>$
|| #The train #have at arrive at #the #ten.
|-
|5) Su trenu devet arrivare a sas deke. || The train should arrive at ten. || ^Su<det><def><m><sg>/The<det><def><m><sg>$ ^trenu<n><m><sg>/train<n><sg>$ ^dèvere<vblex><pri><p3><sg>/shall<vbmod><pri><p3><sg>$ ^arrivare<vblex><inf>/arrive<vblex><inf>$ ^a<pr>/at<pr>/on<pr>/to<pr>$ ^su<det><def><f><pl>/the<det><def><f><pl>$ ^deke<num><mf><sp>/ten<num><mf><sp>$^.<sent>/.<sent>$^.<sent>/.<sent>$
|| #The train #shall arrive at #the #ten.
|-
|6) T'appo natu ki su trenu devíat arrivare a sas deke. || I told you that the train would arrive at ten. || ^Ti<prn><pro><p2><mf><sg>/You<prn><pro><p2><mf><sg>$ ^àere<vbhaver><pri><p1><sg>/have<vbhaver><pri><p1><sg>$ ^nàrrere<vblex><pp><m><sg>/tell<vblex><pp><m><sg>$ ^chi<cnjsub>/that<cnjsub>$ ^su<det><def><m><sg>/the<det><def><m><sg>$ ^trenu<n><m><sg>/train<n><sg>$ ^dèvere<vblex><pii><p3><sg>/shall<vbmod><pii><p3><sg>$ ^arrivare<vblex><inf>/arrive<vblex><inf>$ ^a<pr>/at<pr>/on<pr>/to<pr>$ ^su<det><def><f><pl>/the<det><def><f><pl>$ ^deke<num><mf><sp>/ten<num><mf><sp>$^.<sent>/.<sent>$^.<sent>/.<sent>$
|| #You #have #tell that #the train #shall arrive at #the #ten.
|-
|7) No'isco si at a pròere cras. || I do not know if it will rain tomorrow. || ^No<adv>/Not<adv>$'^iscoare<vblex><pri><p1><sg>/know<vblex><pri><p1><sg>$ ^si<cnjsub>/if<cnjsub>$ ^àere<vbhaver><pri><p3><sg>/have<vbhaver><pri><p3><sg>$ ^a<pr>/at<pr>/on<pr>/to<pr>$ ^pròere<vblex><inf>/rain<vblex><inf>$ ^cras<adv>/tomorrow<adv>$^.<sent>/.<sent>$
|| Not'#know if #have at rain tomorrow

|-
|8) Una de sas berbekes est maláida. || One of the sheep is sick. || ^Unu<num><f><sp>/One<num><f><sp>$ ^de<pr>/to<pr>/of<pr>$ ^su<det><def><f><pl>/the<det><def><f><pl>$ ^berbeke<n><f><pl>/sheep<n><pl>$ ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$ ^malàidu<adj><f><sg>/sick<adj><f><sg>$^.<sent>/.<sent>$
|| #One to #the sheep #be #sick

|-
|9) Appo pèrditu duos de sos libros meos. || I have lost two of my books. || ^Àere<vbhaver><pri><p1><sg>/Have<vbhaver><pri><p1><sg>$ ^pèrdere<vblex><pp><m><sg>/lose<vblex><pp><m><sg>$ ^duos<num><m><sp>/two<num><m><sp>$ ^de<pr>/to<pr>/of<pr>$ ^su<det><def><m><pl>/the<det><def><m><pl>$ ^libru<n><m><pl>/book<n><pl>$ ^meu<prn><pos><m><pl>/my<prn><pos><m><pl>$^.<sent>/.<sent>$

|| #Have #lose #two to #the books #my

|-
|10) M'an natu ki su trenu devíat arrivare a sas nove. || They told me that the train was supposed to arrive at nine. || ^Mi<prn><pro><p1><mf><sg>/I<prn><pro><p1><mf><sg>$ ^àere<vbhaver><pri><p3><pl>/have<vbhaver><pri><p3><pl>$ ^nàrrere<vblex><pp><m><sg>/tell<vblex><pp><m><sg>$ ^chi<cnjsub>/that<cnjsub>$ ^su<det><def><m><sg>/the<det><def><m><sg>$ ^trenu<n><m><sg>/train<n><sg>$ ^dèvere<vblex><pii><p3><sg>/shall<vbmod><pii><p3><sg>$ ^arrivare<vblex><inf>/arrive<vblex><inf>$ ^a<pr>/at<pr>/on<pr>/to<pr>$ ^su<det><def><f><pl>/the<det><def><f><pl>$ ^nove<num><mf><sp>/nine<num><mf><sp>$^.<sent>/.<sent>$
|| #I #have #tell that #the train #shall arrive at #the #nine
|
|}

==expanding lexicon==

{| cellpadding=5
|medas || many || <adj>
|-https://wikis.swarthmore.edu/ling073/index.php?title=Sardinian_and_English&action=edit
|piseddas || girls || <n><pl>
|-
|sun || they are || <v>
|-
|bennidas || to come (home) || <v><pp><fpl>
|-
|balladu || to dance || <v><pp>
|-
|cantaiat || to sing || <v><sg3>
|-
|sos/sa || the || <det>
|-
|piattos || plates || <n><pl>
|-
|mesa || table || <n><sg>
|-
|bi/b' || N/A || <cl>
|-
|problemas || problems || <n><pl>
|-
|unu || one/a || <adj>/<det>
|-
|ube || where || <adv>
|-
|mortu || dead || <v><pp>
|-
|sordatos || soldiers || <n><pl>
|-
|tenimus || we have || <v><pl1>
|-
|frores || flowers || <n><pl>
|-
|keret || to be necessary || <v><sg3>
|-
|mancat || to be missing || <v><sg3>
|-
|ovos || eggs || <n><pl>
|-
|danca || meadow || <n>
|-
|ortu || orchard || <n>
|-
|frade || brother || <n>
|-
|fizza || daughter || <n>
|-
|re || king || <n>
|-
|ora || hour || <n>
|-
|subra || above/on || <prep>
|-
|a || to/at || <prep>
|-
|cumintzos || origins || <n><pl>
|-
|e || and || <conj>
|-
|andamentu || evolution || <n>
|-
|istòricu || historical || <adj>
|-
|de || of/to || <prep>
|-
|sa || the || <det>
|-
|poesia || poetry || <n>
|-
|a bolu || improvised || <adj> (a bolu = improvised, on the fly)
|-
|in || in || <prep>
|-
|sardu || Sardinian || <n>
|-
|logudoresu || Logudorese || <adj>
|-
|non || not || <adv>
|-
|ischit || known || <v><pp>
|-
|meda || much || <adv>
|-
|custu || this || <det><prox>
|-
|artìculu || article || <n>
|-
|chircat || tries || <v><sg3>
|-
|bogare || to bring out || <v>
|-
|pizu || surface || <n> (bogare a pizu = to shed light on, to bring to the surface; see complicated translations of bogare: [http://vocabolariocasu.isresardegna.it/index.php?key=b&int=0&lemmi=cerca&codice=b1264000 here])
|-
|ammentos || memories || <n><pl>
|-
|ammentu || memory || <n>
|-
|ammentare || to remember || <v>
|-
|documentados || documented || <adj>
|-
|si || [null] || <> -- reflexive
|-
|primas || first || <adj>
|-
|disputas || competitions || <n><pl>
|-
|primas || first || <adj>
|-
|tra || between || <prep>
|-
|poetes || poets || <n><pl>
|-
|cale || which || <prn><rel>
|-
|esserent || were || <v> past imperfect 3rd person plural
|-
|règulas || rules, modalities || <n><pl>
|-
|su || the || <det>
|-
|cunfruntu || confrontation || <n>
|-
|sende || being || <v><ger>
|-
|una || a/one || <art>/<adj>
|-
|chirca || research || <n>
|-
|andera || ongoing/progressive || <adj>
|-
|testu || text || <n>
|-
|diat || [null] || <subj><sg3>
|-
|poder || to be able to || <v><inf>
|-
|aer || to have || <v><inf> (also hàere or àere)
|-
|mudonzos || modifications || <n><pl>
|-
|mudonzos || modifications || <n><pl>
|-
|novas || new || <adj><pl>
|-
|noas || data || <n><pl>
|-
|Pro || to || <prep> <-- keep this in mind for lexical selection (to)
|-
|bider || to read || <v><inf>
|-
|artìculu || article || <n>
|-
|sighire || click on || <v><inf>
|-
|intrare || enter || <v><inf>
|-
|desizadu || desired || <adj>
|-
|trenu || train || <n>
|-
|sinke || [null] || <foc>
|-
|fit || was || <v><imp><sg3>
|-
|andande || leaving || <v><ger>
|-
|at || it will || <>
|-
|sas || the || <det>
|-
|deke || ten || <n>
|-
|devet || should || <adv>
|-
|deke || ten || <adj>
|-
|appo || I have || <v><sg1>
|-
|natu || told || <v><pp>
|-
|próere || to rain || <v><inf>
|-
|arrivare || to arrive || <v><inf>
|-
|isco || I know || <v><sg1>
|-
|si || if || <conj>
|-
|ki || that || <conj>
|-
|cras || tomorrow || <adv>
|-
|meos || my || <pos>
|-
|andatos || gone || <adj><pl>
|
|}

===glosses===

Cando so arrivatu a s'istazione, su trenu sink'andaiat

'when I arrived at the station, the train was leaving'

Su trenu sinke fit andande

'The train was leaving"

Su trenu at a arrivare a sas deke

'The train will arrive at ten o'clock'

Su trenu devet arrivare a sas deke

'The train is supposed to arrive at ten o'clock'

T'appo natu ki su trenu diat arrivare a sas deke

'I told you that the train would arrive at ten o'clock'

M'an natu ki su trenu devíat arrivare a sas nove

'They told me that the train was supposed to arrive at nine'

At a próere cras

'It will rain tomorrow'

Devet próere cras

'it is supposed to rain tomorrow'

At a próere cras? Si emmo abbarramus in domo, ma su nono andamus a mare

'Will it rain tomorrow? If so we shall stay at homr, buy if not we will go to the sea'

No'isco si at a próere cras

'I do to know whether it will rain tomorrow'

Una de sas berbekes est maláida

'one of the sheep is sick'

Appo pèrditu duos de sos libros meos

'I have lost two of my books'

Metas de custas pitzinnas sun galanas

'Many of these girls are pretty'

Una pitzinna meta bella

'a very beautiful girl'

Cussas duas bravas pitzinnas

'those two good girls'

unu better cane bellu

'a huge beautiful dog'

un'átteru bette cane

'another huge dog'

Sun andatos a Frantza

'they went to France'

Est ghiratu dae Corsica

'He returned from Corsica'

Connnosco bene sa Frantza

"i know France well'

Custu libru est iscrittu in tedescu

'This book is written in German'

Cussus paráula venit dae su catalanu

'This word comes from Catalan'

Su sardu est una limba antica

'Sardinian is an ancient language'

Appo mandicatu casu

'I ate cheese'

Laura est toddende frores

'Laura is picking flowers'

De frores non nd'appo tódditu

'I did not pick any flowers'

No'amus comporatu pane

'We did not buy bread'

Mandico sa pasta kin casu

'I ate pasta with cheese'

Tres sórrikes an mandicatu tottu su casu

'Three mice ate all the cheese'

semus ponnende vinu in ampullas

'We are putting wine in bottles'

lettu meu esr

'It is my bed'

No'appo lessu libru perunu

'i did not read any book'

Sos k'an furatu si dinari at a èssere punitos

'The people who stole the money will be punished'

Appo invitat sos de Juanne

'I invited Jon's family'

Cussa pinna est sa mea

'That pen is mine'

Cudda mákkina est sa de Juanne

'That car is John's'

Custa ricca at datu mili francos a su vetzu

'This rich woman gave a thousand lira to the old man'

Su guvernu devíat dare ua pensione a dondzi vetzu

'The government should give a pension to every old person'

==External Resources==

*Github repository for [https://github.com/apertium/apertium-srd Sardinian transducer] (and our [https://github.swarthmore.edu/Ling073-sp23/ling073-srd clone])
*Github repository for [https://github.com/apertium/apertium-eng English transducer]
*[https://www.limbasardasudsardigna.it/sar/images/Documenti/Didatica_e_Ainas/Ditzion%C3%A0riu%20Universale%20Rubattu.pdf Dictionary pdf]
*[http://ditzionariu.sardegnacultura.it/it/ Online official dictionary]
*[https://it.glosbe.com/sc/it Web-based machine translator]
*[http://vocabolariocasu.isresardegna.it/index.php?key=a&int=0&lemmi=cerca Sardinian-Italian web-based dictionary]
*[http://www.sardegnadigitallibrary.it/mmt/fullsize/2009050512495700047.pdf 1931 pdf with select translations]
*[https://onlinelibrary.wiley.com/doi/epdf/10.1111/j.0079-1636.2004.00130.x Definiteness effects: evidence from Sardinian]
*[https://www.icongrouponline.com/en/Detail/dictionary/049783698X/Webster%27s+Sardinian+-+English+Thesaurus+Dictionary: Webster's Sardinian English Thesaurus Dictionary]
*[https://www.academia.edu/15320922/Dizionario_della_lingua_Sarda_Vol_2 Italian-Sardinian Dictionary]
*[https://archive.org/details/vocabolariosardo00spanuoft/page/n361/mode/2up Old but extensive Sardo-Italian and vice versa dictionary]
*[https://limbasardasudsardigna.it/sar/images/Documenti/Didatica_e_Ainas/Vocabolariu_Sardu_Italianu_Spano.pdf nice Sardo-Italiano dictionary pdf]
*[http://www.fontesarda.it/sr/sr0045.htm Conjugations of "to have" in Sardinian]
*[https://sinnainotizie.com/2015/03/07/lezioni-di-grammatica-sardo-campidanese-undicesima-lezione-su-verbu-ai-aere/ Whole Sardinian grammar page about conjugations of to have all written in Sardinian language!]
*Sardinian grammar:[https://www.limbasardasudsardigna.it/sar/images/Documenti/Didatica_e_Ainas/grammatiga_sardo%20campidanese%20A.LEPORI.pdf pdf]
[[Category:Sp23_TranslationPairs]],[[Category:Sardinian]],[[Category:English]]

Sardinian and English

2023-05-04T18:01:40Z

Rorlija1: /* Final evaluation */

=Resources for Machine Translation from Sardinian to English=

==Developed Resources==
*[https://github.swarthmore.edu/Ling073-sp23/ling073-srd-eng-corpus Parallel corpus git repo].
*:Lines 1-8 from [http://maxia-mail.doomby.com/ this website].
*[https://github.swarthmore.edu/Ling073-sp23/ling073-srd-eng Git repo for language pair]
*[https://github.swarthmore.edu/Ling073-sp23/ling073-srd Git repo for Sardinian]
*[https://github.com/apertium/apertium-eng Forked git repo for English]
*[https://wikis.swarthmore.edu/ling073/Sardinian_and_English/Lexical_selection#srd_.E2.86.92_eng Lexical selection wiki]
*[https://wikis.swarthmore.edu/ling073/Sardinian_and_English/Contrastive_Grammar#Differences_in_parse_and_corresponding_examples Contrastive grammar wiki]
*[https://wikis.swarthmore.edu/ling073/Sardinian_and_English/Structural_transfer Structural transfer wiki]

==srd → eng evaluation==
*coverage of monolingual Sardinian transducer on srd.sentences.txt:
Number of tokenised words in the corpus: 262
Coverage: 94.66%
*coverage of bilingual transducer on srd.sentences
Number of tokenised words in the corpus: 266
Coverage: 85.71%

==Additions for polished RBMT system==
*Over 100 new stems to bilingual dictionary
*:(now we have 172 total entries in the .dix file)
*4 sets of lexical selection rules
*:(now we have rules that solve 5 problems in total)
*3 items from contrastive grammar implemented in transfer rules
*:(now we have rules that implement 4 total items)

==Final evaluation==
* For the monolingual transducer:
** Updated precision and recall against the (updated) <code>eval.test</code> and <code>eval.gold</code> files
** Coverage over the <code>large</code> corpus:
** The number of words in the <code>large</code> corpus,
** The number of stems in the transducer.

* For MT in the direction we developed (<code>srd-eng</code>):
** WER and PER over <code>longer</code> corpus:
-------------------------------------------------------
Number of words in reference: 315
Number of words in test: 341
Number of unknown words (marked with a star) in test: 35
Percentage of unknown words: 10.26 %

Results when removing unknown-word marks (stars)
-------------------------------------------------------
Edit distance: 246
Word error rate (WER): 78.10 %
Number of position-independent correct words: 118
Position-independent word error rate (PER): 70.79 %
** The proportion of stems translated correctly in the <code>longer</code> corpus.
** Trimmed coverage over <code>longer</code> and <code>large</code> corpora.
** The number of tokens in <code>longer</code> and <code>large</code> corpora.

==10 sentences glosses and outputs==
*Note: '''These are outputs at end of lexical transfer before lexical selection and other weeks' improvements were implemented'''
{| cellpadding=5
|Sardinian sentence || intended English translation || output of srd-eng-biltrans (lexical transfer) mode || output of srd-eng (full translation) mode
|-
|1) Su sardu est una limba antica. || Sardinian is an ancient language. || ^Su<det><def><m><sg>/The<det><def><m><sg>$ ^sardu<n><m><sg>/Sardinian<n><sg>$ ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$ ^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$^.<sent>/.<sent>$^.<sent>/.<sent>$
|| #The Sardinian #be #a language #ancient
|-
|2) Pro bider s'artìculu sighire custu culligamentu. || To read the article click on this link. || ^Pro<pr>/For<pr>/To<pr>$ ^bider<vblex><inf>/read<vblex><inf>$ ^su<det><def><mf><sg>/the<det><def><mf><sg>$ ^artìculu<n><m><sg>/article<n><sg>$ ^sighire<vblex><inf>/click<vblex><inf>$ ^custu<det><dem><m><sg>/this<det><m><sg>$ ^culligamentu<n><m><sg>/link<n><sg>$^.<sent>/.<sent>$^.<sent>/.<sent>$<m><sg>$ ^culligamentu<n><m><sg>/link<n><sg>$^.<sent>/.<sent>$^.<sent>/.<sent>$
|| For read #the article click #this link.
|-
|3) Su trenu sinke fit andande. || The train was leaving. || ^Su<det><def><m><sg>/The<det><def><m><sg>$ ^trenu<n><m><sg>/train<n><sg>$ ^sinke<cnjadv>/$ ^èssere<vbser><pii><p3><sg>/be<vbser><pii><p3><sg>$ ^andare<vblex><ger>/leave<vblex><ger>/go<vblex><ger>$^.<sent>/.<sent>$^.<sent>/.<sent>$

|| #The train #be leaving.
|-
|4) Su trenu at a arrivare a sas deke. || The train will arrive at ten. || ^Su<det><def><m><sg>/The<det><def><m><sg>$ ^trenu<n><m><sg>/train<n><sg>$ ^àere<vbhaver><pri><p3><sg>/have<vbhaver><pri><p3><sg>$ ^a<pr>/at<pr>/on<pr>/to<pr>$ ^arrivare<vblex><inf>/arrive<vblex><inf>$ ^a<pr>/at<pr>/on<pr>/to<pr>$ ^su<det><def><f><pl>/the<det><def><f><pl>$ ^deke<num><mf><sp>/ten<num><mf><sp>$^.<sent>/.<sent>$^.<sent>/.<sent>$
|| #The train #have at arrive at #the #ten.
|-
|5) Su trenu devet arrivare a sas deke. || The train should arrive at ten. || ^Su<det><def><m><sg>/The<det><def><m><sg>$ ^trenu<n><m><sg>/train<n><sg>$ ^dèvere<vblex><pri><p3><sg>/shall<vbmod><pri><p3><sg>$ ^arrivare<vblex><inf>/arrive<vblex><inf>$ ^a<pr>/at<pr>/on<pr>/to<pr>$ ^su<det><def><f><pl>/the<det><def><f><pl>$ ^deke<num><mf><sp>/ten<num><mf><sp>$^.<sent>/.<sent>$^.<sent>/.<sent>$
|| #The train #shall arrive at #the #ten.
|-
|6) T'appo natu ki su trenu devíat arrivare a sas deke. || I told you that the train would arrive at ten. || ^Ti<prn><pro><p2><mf><sg>/You<prn><pro><p2><mf><sg>$ ^àere<vbhaver><pri><p1><sg>/have<vbhaver><pri><p1><sg>$ ^nàrrere<vblex><pp><m><sg>/tell<vblex><pp><m><sg>$ ^chi<cnjsub>/that<cnjsub>$ ^su<det><def><m><sg>/the<det><def><m><sg>$ ^trenu<n><m><sg>/train<n><sg>$ ^dèvere<vblex><pii><p3><sg>/shall<vbmod><pii><p3><sg>$ ^arrivare<vblex><inf>/arrive<vblex><inf>$ ^a<pr>/at<pr>/on<pr>/to<pr>$ ^su<det><def><f><pl>/the<det><def><f><pl>$ ^deke<num><mf><sp>/ten<num><mf><sp>$^.<sent>/.<sent>$^.<sent>/.<sent>$
|| #You #have #tell that #the train #shall arrive at #the #ten.
|-
|7) No'isco si at a pròere cras. || I do not know if it will rain tomorrow. || ^No<adv>/Not<adv>$'^iscoare<vblex><pri><p1><sg>/know<vblex><pri><p1><sg>$ ^si<cnjsub>/if<cnjsub>$ ^àere<vbhaver><pri><p3><sg>/have<vbhaver><pri><p3><sg>$ ^a<pr>/at<pr>/on<pr>/to<pr>$ ^pròere<vblex><inf>/rain<vblex><inf>$ ^cras<adv>/tomorrow<adv>$^.<sent>/.<sent>$
|| Not'#know if #have at rain tomorrow

|-
|8) Una de sas berbekes est maláida. || One of the sheep is sick. || ^Unu<num><f><sp>/One<num><f><sp>$ ^de<pr>/to<pr>/of<pr>$ ^su<det><def><f><pl>/the<det><def><f><pl>$ ^berbeke<n><f><pl>/sheep<n><pl>$ ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$ ^malàidu<adj><f><sg>/sick<adj><f><sg>$^.<sent>/.<sent>$
|| #One to #the sheep #be #sick

|-
|9) Appo pèrditu duos de sos libros meos. || I have lost two of my books. || ^Àere<vbhaver><pri><p1><sg>/Have<vbhaver><pri><p1><sg>$ ^pèrdere<vblex><pp><m><sg>/lose<vblex><pp><m><sg>$ ^duos<num><m><sp>/two<num><m><sp>$ ^de<pr>/to<pr>/of<pr>$ ^su<det><def><m><pl>/the<det><def><m><pl>$ ^libru<n><m><pl>/book<n><pl>$ ^meu<prn><pos><m><pl>/my<prn><pos><m><pl>$^.<sent>/.<sent>$

|| #Have #lose #two to #the books #my

|-
|10) M'an natu ki su trenu devíat arrivare a sas nove. || They told me that the train was supposed to arrive at nine. || ^Mi<prn><pro><p1><mf><sg>/I<prn><pro><p1><mf><sg>$ ^àere<vbhaver><pri><p3><pl>/have<vbhaver><pri><p3><pl>$ ^nàrrere<vblex><pp><m><sg>/tell<vblex><pp><m><sg>$ ^chi<cnjsub>/that<cnjsub>$ ^su<det><def><m><sg>/the<det><def><m><sg>$ ^trenu<n><m><sg>/train<n><sg>$ ^dèvere<vblex><pii><p3><sg>/shall<vbmod><pii><p3><sg>$ ^arrivare<vblex><inf>/arrive<vblex><inf>$ ^a<pr>/at<pr>/on<pr>/to<pr>$ ^su<det><def><f><pl>/the<det><def><f><pl>$ ^nove<num><mf><sp>/nine<num><mf><sp>$^.<sent>/.<sent>$
|| #I #have #tell that #the train #shall arrive at #the #nine
|
|}

==expanding lexicon==

{| cellpadding=5
|medas || many || <adj>
|-https://wikis.swarthmore.edu/ling073/index.php?title=Sardinian_and_English&action=edit
|piseddas || girls || <n><pl>
|-
|sun || they are || <v>
|-
|bennidas || to come (home) || <v><pp><fpl>
|-
|balladu || to dance || <v><pp>
|-
|cantaiat || to sing || <v><sg3>
|-
|sos/sa || the || <det>
|-
|piattos || plates || <n><pl>
|-
|mesa || table || <n><sg>
|-
|bi/b' || N/A || <cl>
|-
|problemas || problems || <n><pl>
|-
|unu || one/a || <adj>/<det>
|-
|ube || where || <adv>
|-
|mortu || dead || <v><pp>
|-
|sordatos || soldiers || <n><pl>
|-
|tenimus || we have || <v><pl1>
|-
|frores || flowers || <n><pl>
|-
|keret || to be necessary || <v><sg3>
|-
|mancat || to be missing || <v><sg3>
|-
|ovos || eggs || <n><pl>
|-
|danca || meadow || <n>
|-
|ortu || orchard || <n>
|-
|frade || brother || <n>
|-
|fizza || daughter || <n>
|-
|re || king || <n>
|-
|ora || hour || <n>
|-
|subra || above/on || <prep>
|-
|a || to/at || <prep>
|-
|cumintzos || origins || <n><pl>
|-
|e || and || <conj>
|-
|andamentu || evolution || <n>
|-
|istòricu || historical || <adj>
|-
|de || of/to || <prep>
|-
|sa || the || <det>
|-
|poesia || poetry || <n>
|-
|a bolu || improvised || <adj> (a bolu = improvised, on the fly)
|-
|in || in || <prep>
|-
|sardu || Sardinian || <n>
|-
|logudoresu || Logudorese || <adj>
|-
|non || not || <adv>
|-
|ischit || known || <v><pp>
|-
|meda || much || <adv>
|-
|custu || this || <det><prox>
|-
|artìculu || article || <n>
|-
|chircat || tries || <v><sg3>
|-
|bogare || to bring out || <v>
|-
|pizu || surface || <n> (bogare a pizu = to shed light on, to bring to the surface; see complicated translations of bogare: [http://vocabolariocasu.isresardegna.it/index.php?key=b&int=0&lemmi=cerca&codice=b1264000 here])
|-
|ammentos || memories || <n><pl>
|-
|ammentu || memory || <n>
|-
|ammentare || to remember || <v>
|-
|documentados || documented || <adj>
|-
|si || [null] || <> -- reflexive
|-
|primas || first || <adj>
|-
|disputas || competitions || <n><pl>
|-
|primas || first || <adj>
|-
|tra || between || <prep>
|-
|poetes || poets || <n><pl>
|-
|cale || which || <prn><rel>
|-
|esserent || were || <v> past imperfect 3rd person plural
|-
|règulas || rules, modalities || <n><pl>
|-
|su || the || <det>
|-
|cunfruntu || confrontation || <n>
|-
|sende || being || <v><ger>
|-
|una || a/one || <art>/<adj>
|-
|chirca || research || <n>
|-
|andera || ongoing/progressive || <adj>
|-
|testu || text || <n>
|-
|diat || [null] || <subj><sg3>
|-
|poder || to be able to || <v><inf>
|-
|aer || to have || <v><inf> (also hàere or àere)
|-
|mudonzos || modifications || <n><pl>
|-
|mudonzos || modifications || <n><pl>
|-
|novas || new || <adj><pl>
|-
|noas || data || <n><pl>
|-
|Pro || to || <prep> <-- keep this in mind for lexical selection (to)
|-
|bider || to read || <v><inf>
|-
|artìculu || article || <n>
|-
|sighire || click on || <v><inf>
|-
|intrare || enter || <v><inf>
|-
|desizadu || desired || <adj>
|-
|trenu || train || <n>
|-
|sinke || [null] || <foc>
|-
|fit || was || <v><imp><sg3>
|-
|andande || leaving || <v><ger>
|-
|at || it will || <>
|-
|sas || the || <det>
|-
|deke || ten || <n>
|-
|devet || should || <adv>
|-
|deke || ten || <adj>
|-
|appo || I have || <v><sg1>
|-
|natu || told || <v><pp>
|-
|próere || to rain || <v><inf>
|-
|arrivare || to arrive || <v><inf>
|-
|isco || I know || <v><sg1>
|-
|si || if || <conj>
|-
|ki || that || <conj>
|-
|cras || tomorrow || <adv>
|-
|meos || my || <pos>
|-
|andatos || gone || <adj><pl>
|
|}

===glosses===

Cando so arrivatu a s'istazione, su trenu sink'andaiat

'when I arrived at the station, the train was leaving'

Su trenu sinke fit andande

'The train was leaving"

Su trenu at a arrivare a sas deke

'The train will arrive at ten o'clock'

Su trenu devet arrivare a sas deke

'The train is supposed to arrive at ten o'clock'

T'appo natu ki su trenu diat arrivare a sas deke

'I told you that the train would arrive at ten o'clock'

M'an natu ki su trenu devíat arrivare a sas nove

'They told me that the train was supposed to arrive at nine'

At a próere cras

'It will rain tomorrow'

Devet próere cras

'it is supposed to rain tomorrow'

At a próere cras? Si emmo abbarramus in domo, ma su nono andamus a mare

'Will it rain tomorrow? If so we shall stay at homr, buy if not we will go to the sea'

No'isco si at a próere cras

'I do to know whether it will rain tomorrow'

Una de sas berbekes est maláida

'one of the sheep is sick'

Appo pèrditu duos de sos libros meos

'I have lost two of my books'

Metas de custas pitzinnas sun galanas

'Many of these girls are pretty'

Una pitzinna meta bella

'a very beautiful girl'

Cussas duas bravas pitzinnas

'those two good girls'

unu better cane bellu

'a huge beautiful dog'

un'átteru bette cane

'another huge dog'

Sun andatos a Frantza

'they went to France'

Est ghiratu dae Corsica

'He returned from Corsica'

Connnosco bene sa Frantza

"i know France well'

Custu libru est iscrittu in tedescu

'This book is written in German'

Cussus paráula venit dae su catalanu

'This word comes from Catalan'

Su sardu est una limba antica

'Sardinian is an ancient language'

Appo mandicatu casu

'I ate cheese'

Laura est toddende frores

'Laura is picking flowers'

De frores non nd'appo tódditu

'I did not pick any flowers'

No'amus comporatu pane

'We did not buy bread'

Mandico sa pasta kin casu

'I ate pasta with cheese'

Tres sórrikes an mandicatu tottu su casu

'Three mice ate all the cheese'

semus ponnende vinu in ampullas

'We are putting wine in bottles'

lettu meu esr

'It is my bed'

No'appo lessu libru perunu

'i did not read any book'

Sos k'an furatu si dinari at a èssere punitos

'The people who stole the money will be punished'

Appo invitat sos de Juanne

'I invited Jon's family'

Cussa pinna est sa mea

'That pen is mine'

Cudda mákkina est sa de Juanne

'That car is John's'

Custa ricca at datu mili francos a su vetzu

'This rich woman gave a thousand lira to the old man'

Su guvernu devíat dare ua pensione a dondzi vetzu

'The government should give a pension to every old person'

==External Resources==

*Github repository for [https://github.com/apertium/apertium-srd Sardinian transducer] (and our [https://github.swarthmore.edu/Ling073-sp23/ling073-srd clone])
*Github repository for [https://github.com/apertium/apertium-eng English transducer]
*[https://www.limbasardasudsardigna.it/sar/images/Documenti/Didatica_e_Ainas/Ditzion%C3%A0riu%20Universale%20Rubattu.pdf Dictionary pdf]
*[http://ditzionariu.sardegnacultura.it/it/ Online official dictionary]
*[https://it.glosbe.com/sc/it Web-based machine translator]
*[http://vocabolariocasu.isresardegna.it/index.php?key=a&int=0&lemmi=cerca Sardinian-Italian web-based dictionary]
*[http://www.sardegnadigitallibrary.it/mmt/fullsize/2009050512495700047.pdf 1931 pdf with select translations]
*[https://onlinelibrary.wiley.com/doi/epdf/10.1111/j.0079-1636.2004.00130.x Definiteness effects: evidence from Sardinian]
*[https://www.icongrouponline.com/en/Detail/dictionary/049783698X/Webster%27s+Sardinian+-+English+Thesaurus+Dictionary: Webster's Sardinian English Thesaurus Dictionary]
*[https://www.academia.edu/15320922/Dizionario_della_lingua_Sarda_Vol_2 Italian-Sardinian Dictionary]
*[https://archive.org/details/vocabolariosardo00spanuoft/page/n361/mode/2up Old but extensive Sardo-Italian and vice versa dictionary]
*[https://limbasardasudsardigna.it/sar/images/Documenti/Didatica_e_Ainas/Vocabolariu_Sardu_Italianu_Spano.pdf nice Sardo-Italiano dictionary pdf]
*[http://www.fontesarda.it/sr/sr0045.htm Conjugations of "to have" in Sardinian]
*[https://sinnainotizie.com/2015/03/07/lezioni-di-grammatica-sardo-campidanese-undicesima-lezione-su-verbu-ai-aere/ Whole Sardinian grammar page about conjugations of to have all written in Sardinian language!]
*Sardinian grammar:[https://www.limbasardasudsardigna.it/sar/images/Documenti/Didatica_e_Ainas/grammatiga_sardo%20campidanese%20A.LEPORI.pdf pdf]
[[Category:Sp23_TranslationPairs]],[[Category:Sardinian]],[[Category:English]]

Sardinian and English

2023-05-04T16:41:45Z

Rorlija1: /* Final evaluation */

=Resources for Machine Translation from Sardinian to English=

==Developed Resources==
*[https://github.swarthmore.edu/Ling073-sp23/ling073-srd-eng-corpus Parallel corpus git repo].
*:Lines 1-8 from [http://maxia-mail.doomby.com/ this website].
*[https://github.swarthmore.edu/Ling073-sp23/ling073-srd-eng Git repo for language pair]
*[https://github.swarthmore.edu/Ling073-sp23/ling073-srd Git repo for Sardinian]
*[https://github.com/apertium/apertium-eng Forked git repo for English]
*[https://wikis.swarthmore.edu/ling073/Sardinian_and_English/Lexical_selection#srd_.E2.86.92_eng Lexical selection wiki]
*[https://wikis.swarthmore.edu/ling073/Sardinian_and_English/Contrastive_Grammar#Differences_in_parse_and_corresponding_examples Contrastive grammar wiki]
*[https://wikis.swarthmore.edu/ling073/Sardinian_and_English/Structural_transfer Structural transfer wiki]

==srd → eng evaluation==
*coverage of monolingual Sardinian transducer on srd.sentences.txt:
Number of tokenised words in the corpus: 262
Coverage: 94.66%
*coverage of bilingual transducer on srd.sentences
Number of tokenised words in the corpus: 266
Coverage: 85.71%

==Additions for polished RBMT system==
*Over 100 new stems to bilingual dictionary
*:(now we have 172 total entries in the .dix file)
*4 sets of lexical selection rules
*:(now we have rules that solve 5 problems in total)
*3 items from contrastive grammar implemented in transfer rules
*:(now we have rules that implement 4 total items)

==Final evaluation==
* For the monolingual transducer:
** Updated precision and recall against the (updated) <code>eval.test</code> and <code>eval.gold</code> files
** Coverage over the <code>large</code> corpus:
** The number of words in the <code>large</code> corpus,
** The number of stems in the transducer.
* For MT in the direction we developed (<code>srd-eng</code>):
** WER and PER over <code>longer</code> corpus:
** The proportion of stems translated correctly in the <code>longer</code> corpus.
** Trimmed coverage over <code>longer</code> and <code>large</code> corpora.
** The number of tokens in <code>longer</code> and <code>large</code> corpora.

==10 sentences glosses and outputs==
*Note: '''These are outputs at end of lexical transfer before lexical selection and other weeks' improvements were implemented'''
{| cellpadding=5
|Sardinian sentence || intended English translation || output of srd-eng-biltrans (lexical transfer) mode || output of srd-eng (full translation) mode
|-
|1) Su sardu est una limba antica. || Sardinian is an ancient language. || ^Su<det><def><m><sg>/The<det><def><m><sg>$ ^sardu<n><m><sg>/Sardinian<n><sg>$ ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$ ^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$^.<sent>/.<sent>$^.<sent>/.<sent>$
|| #The Sardinian #be #a language #ancient
|-
|2) Pro bider s'artìculu sighire custu culligamentu. || To read the article click on this link. || ^Pro<pr>/For<pr>/To<pr>$ ^bider<vblex><inf>/read<vblex><inf>$ ^su<det><def><mf><sg>/the<det><def><mf><sg>$ ^artìculu<n><m><sg>/article<n><sg>$ ^sighire<vblex><inf>/click<vblex><inf>$ ^custu<det><dem><m><sg>/this<det><m><sg>$ ^culligamentu<n><m><sg>/link<n><sg>$^.<sent>/.<sent>$^.<sent>/.<sent>$<m><sg>$ ^culligamentu<n><m><sg>/link<n><sg>$^.<sent>/.<sent>$^.<sent>/.<sent>$
|| For read #the article click #this link.
|-
|3) Su trenu sinke fit andande. || The train was leaving. || ^Su<det><def><m><sg>/The<det><def><m><sg>$ ^trenu<n><m><sg>/train<n><sg>$ ^sinke<cnjadv>/$ ^èssere<vbser><pii><p3><sg>/be<vbser><pii><p3><sg>$ ^andare<vblex><ger>/leave<vblex><ger>/go<vblex><ger>$^.<sent>/.<sent>$^.<sent>/.<sent>$

|| #The train #be leaving.
|-
|4) Su trenu at a arrivare a sas deke. || The train will arrive at ten. || ^Su<det><def><m><sg>/The<det><def><m><sg>$ ^trenu<n><m><sg>/train<n><sg>$ ^àere<vbhaver><pri><p3><sg>/have<vbhaver><pri><p3><sg>$ ^a<pr>/at<pr>/on<pr>/to<pr>$ ^arrivare<vblex><inf>/arrive<vblex><inf>$ ^a<pr>/at<pr>/on<pr>/to<pr>$ ^su<det><def><f><pl>/the<det><def><f><pl>$ ^deke<num><mf><sp>/ten<num><mf><sp>$^.<sent>/.<sent>$^.<sent>/.<sent>$
|| #The train #have at arrive at #the #ten.
|-
|5) Su trenu devet arrivare a sas deke. || The train should arrive at ten. || ^Su<det><def><m><sg>/The<det><def><m><sg>$ ^trenu<n><m><sg>/train<n><sg>$ ^dèvere<vblex><pri><p3><sg>/shall<vbmod><pri><p3><sg>$ ^arrivare<vblex><inf>/arrive<vblex><inf>$ ^a<pr>/at<pr>/on<pr>/to<pr>$ ^su<det><def><f><pl>/the<det><def><f><pl>$ ^deke<num><mf><sp>/ten<num><mf><sp>$^.<sent>/.<sent>$^.<sent>/.<sent>$
|| #The train #shall arrive at #the #ten.
|-
|6) T'appo natu ki su trenu devíat arrivare a sas deke. || I told you that the train would arrive at ten. || ^Ti<prn><pro><p2><mf><sg>/You<prn><pro><p2><mf><sg>$ ^àere<vbhaver><pri><p1><sg>/have<vbhaver><pri><p1><sg>$ ^nàrrere<vblex><pp><m><sg>/tell<vblex><pp><m><sg>$ ^chi<cnjsub>/that<cnjsub>$ ^su<det><def><m><sg>/the<det><def><m><sg>$ ^trenu<n><m><sg>/train<n><sg>$ ^dèvere<vblex><pii><p3><sg>/shall<vbmod><pii><p3><sg>$ ^arrivare<vblex><inf>/arrive<vblex><inf>$ ^a<pr>/at<pr>/on<pr>/to<pr>$ ^su<det><def><f><pl>/the<det><def><f><pl>$ ^deke<num><mf><sp>/ten<num><mf><sp>$^.<sent>/.<sent>$^.<sent>/.<sent>$
|| #You #have #tell that #the train #shall arrive at #the #ten.
|-
|7) No'isco si at a pròere cras. || I do not know if it will rain tomorrow. || ^No<adv>/Not<adv>$'^iscoare<vblex><pri><p1><sg>/know<vblex><pri><p1><sg>$ ^si<cnjsub>/if<cnjsub>$ ^àere<vbhaver><pri><p3><sg>/have<vbhaver><pri><p3><sg>$ ^a<pr>/at<pr>/on<pr>/to<pr>$ ^pròere<vblex><inf>/rain<vblex><inf>$ ^cras<adv>/tomorrow<adv>$^.<sent>/.<sent>$
|| Not'#know if #have at rain tomorrow

|-
|8) Una de sas berbekes est maláida. || One of the sheep is sick. || ^Unu<num><f><sp>/One<num><f><sp>$ ^de<pr>/to<pr>/of<pr>$ ^su<det><def><f><pl>/the<det><def><f><pl>$ ^berbeke<n><f><pl>/sheep<n><pl>$ ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$ ^malàidu<adj><f><sg>/sick<adj><f><sg>$^.<sent>/.<sent>$
|| #One to #the sheep #be #sick

|-
|9) Appo pèrditu duos de sos libros meos. || I have lost two of my books. || ^Àere<vbhaver><pri><p1><sg>/Have<vbhaver><pri><p1><sg>$ ^pèrdere<vblex><pp><m><sg>/lose<vblex><pp><m><sg>$ ^duos<num><m><sp>/two<num><m><sp>$ ^de<pr>/to<pr>/of<pr>$ ^su<det><def><m><pl>/the<det><def><m><pl>$ ^libru<n><m><pl>/book<n><pl>$ ^meu<prn><pos><m><pl>/my<prn><pos><m><pl>$^.<sent>/.<sent>$

|| #Have #lose #two to #the books #my

|-
|10) M'an natu ki su trenu devíat arrivare a sas nove. || They told me that the train was supposed to arrive at nine. || ^Mi<prn><pro><p1><mf><sg>/I<prn><pro><p1><mf><sg>$ ^àere<vbhaver><pri><p3><pl>/have<vbhaver><pri><p3><pl>$ ^nàrrere<vblex><pp><m><sg>/tell<vblex><pp><m><sg>$ ^chi<cnjsub>/that<cnjsub>$ ^su<det><def><m><sg>/the<det><def><m><sg>$ ^trenu<n><m><sg>/train<n><sg>$ ^dèvere<vblex><pii><p3><sg>/shall<vbmod><pii><p3><sg>$ ^arrivare<vblex><inf>/arrive<vblex><inf>$ ^a<pr>/at<pr>/on<pr>/to<pr>$ ^su<det><def><f><pl>/the<det><def><f><pl>$ ^nove<num><mf><sp>/nine<num><mf><sp>$^.<sent>/.<sent>$
|| #I #have #tell that #the train #shall arrive at #the #nine
|
|}

==expanding lexicon==

{| cellpadding=5
|medas || many || <adj>
|-https://wikis.swarthmore.edu/ling073/index.php?title=Sardinian_and_English&action=edit
|piseddas || girls || <n><pl>
|-
|sun || they are || <v>
|-
|bennidas || to come (home) || <v><pp><fpl>
|-
|balladu || to dance || <v><pp>
|-
|cantaiat || to sing || <v><sg3>
|-
|sos/sa || the || <det>
|-
|piattos || plates || <n><pl>
|-
|mesa || table || <n><sg>
|-
|bi/b' || N/A || <cl>
|-
|problemas || problems || <n><pl>
|-
|unu || one/a || <adj>/<det>
|-
|ube || where || <adv>
|-
|mortu || dead || <v><pp>
|-
|sordatos || soldiers || <n><pl>
|-
|tenimus || we have || <v><pl1>
|-
|frores || flowers || <n><pl>
|-
|keret || to be necessary || <v><sg3>
|-
|mancat || to be missing || <v><sg3>
|-
|ovos || eggs || <n><pl>
|-
|danca || meadow || <n>
|-
|ortu || orchard || <n>
|-
|frade || brother || <n>
|-
|fizza || daughter || <n>
|-
|re || king || <n>
|-
|ora || hour || <n>
|-
|subra || above/on || <prep>
|-
|a || to/at || <prep>
|-
|cumintzos || origins || <n><pl>
|-
|e || and || <conj>
|-
|andamentu || evolution || <n>
|-
|istòricu || historical || <adj>
|-
|de || of/to || <prep>
|-
|sa || the || <det>
|-
|poesia || poetry || <n>
|-
|a bolu || improvised || <adj> (a bolu = improvised, on the fly)
|-
|in || in || <prep>
|-
|sardu || Sardinian || <n>
|-
|logudoresu || Logudorese || <adj>
|-
|non || not || <adv>
|-
|ischit || known || <v><pp>
|-
|meda || much || <adv>
|-
|custu || this || <det><prox>
|-
|artìculu || article || <n>
|-
|chircat || tries || <v><sg3>
|-
|bogare || to bring out || <v>
|-
|pizu || surface || <n> (bogare a pizu = to shed light on, to bring to the surface; see complicated translations of bogare: [http://vocabolariocasu.isresardegna.it/index.php?key=b&int=0&lemmi=cerca&codice=b1264000 here])
|-
|ammentos || memories || <n><pl>
|-
|ammentu || memory || <n>
|-
|ammentare || to remember || <v>
|-
|documentados || documented || <adj>
|-
|si || [null] || <> -- reflexive
|-
|primas || first || <adj>
|-
|disputas || competitions || <n><pl>
|-
|primas || first || <adj>
|-
|tra || between || <prep>
|-
|poetes || poets || <n><pl>
|-
|cale || which || <prn><rel>
|-
|esserent || were || <v> past imperfect 3rd person plural
|-
|règulas || rules, modalities || <n><pl>
|-
|su || the || <det>
|-
|cunfruntu || confrontation || <n>
|-
|sende || being || <v><ger>
|-
|una || a/one || <art>/<adj>
|-
|chirca || research || <n>
|-
|andera || ongoing/progressive || <adj>
|-
|testu || text || <n>
|-
|diat || [null] || <subj><sg3>
|-
|poder || to be able to || <v><inf>
|-
|aer || to have || <v><inf> (also hàere or àere)
|-
|mudonzos || modifications || <n><pl>
|-
|mudonzos || modifications || <n><pl>
|-
|novas || new || <adj><pl>
|-
|noas || data || <n><pl>
|-
|Pro || to || <prep> <-- keep this in mind for lexical selection (to)
|-
|bider || to read || <v><inf>
|-
|artìculu || article || <n>
|-
|sighire || click on || <v><inf>
|-
|intrare || enter || <v><inf>
|-
|desizadu || desired || <adj>
|-
|trenu || train || <n>
|-
|sinke || [null] || <foc>
|-
|fit || was || <v><imp><sg3>
|-
|andande || leaving || <v><ger>
|-
|at || it will || <>
|-
|sas || the || <det>
|-
|deke || ten || <n>
|-
|devet || should || <adv>
|-
|deke || ten || <adj>
|-
|appo || I have || <v><sg1>
|-
|natu || told || <v><pp>
|-
|próere || to rain || <v><inf>
|-
|arrivare || to arrive || <v><inf>
|-
|isco || I know || <v><sg1>
|-
|si || if || <conj>
|-
|ki || that || <conj>
|-
|cras || tomorrow || <adv>
|-
|meos || my || <pos>
|-
|andatos || gone || <adj><pl>
|
|}

===glosses===

Cando so arrivatu a s'istazione, su trenu sink'andaiat

'when I arrived at the station, the train was leaving'

Su trenu sinke fit andande

'The train was leaving"

Su trenu at a arrivare a sas deke

'The train will arrive at ten o'clock'

Su trenu devet arrivare a sas deke

'The train is supposed to arrive at ten o'clock'

T'appo natu ki su trenu diat arrivare a sas deke

'I told you that the train would arrive at ten o'clock'

M'an natu ki su trenu devíat arrivare a sas nove

'They told me that the train was supposed to arrive at nine'

At a próere cras

'It will rain tomorrow'

Devet próere cras

'it is supposed to rain tomorrow'

At a próere cras? Si emmo abbarramus in domo, ma su nono andamus a mare

'Will it rain tomorrow? If so we shall stay at homr, buy if not we will go to the sea'

No'isco si at a próere cras

'I do to know whether it will rain tomorrow'

Una de sas berbekes est maláida

'one of the sheep is sick'

Appo pèrditu duos de sos libros meos

'I have lost two of my books'

Metas de custas pitzinnas sun galanas

'Many of these girls are pretty'

Una pitzinna meta bella

'a very beautiful girl'

Cussas duas bravas pitzinnas

'those two good girls'

unu better cane bellu

'a huge beautiful dog'

un'átteru bette cane

'another huge dog'

Sun andatos a Frantza

'they went to France'

Est ghiratu dae Corsica

'He returned from Corsica'

Connnosco bene sa Frantza

"i know France well'

Custu libru est iscrittu in tedescu

'This book is written in German'

Cussus paráula venit dae su catalanu

'This word comes from Catalan'

Su sardu est una limba antica

'Sardinian is an ancient language'

Appo mandicatu casu

'I ate cheese'

Laura est toddende frores

'Laura is picking flowers'

De frores non nd'appo tódditu

'I did not pick any flowers'

No'amus comporatu pane

'We did not buy bread'

Mandico sa pasta kin casu

'I ate pasta with cheese'

Tres sórrikes an mandicatu tottu su casu

'Three mice ate all the cheese'

semus ponnende vinu in ampullas

'We are putting wine in bottles'

lettu meu esr

'It is my bed'

No'appo lessu libru perunu

'i did not read any book'

Sos k'an furatu si dinari at a èssere punitos

'The people who stole the money will be punished'

Appo invitat sos de Juanne

'I invited Jon's family'

Cussa pinna est sa mea

'That pen is mine'

Cudda mákkina est sa de Juanne

'That car is John's'

Custa ricca at datu mili francos a su vetzu

'This rich woman gave a thousand lira to the old man'

Su guvernu devíat dare ua pensione a dondzi vetzu

'The government should give a pension to every old person'

==External Resources==

*Github repository for [https://github.com/apertium/apertium-srd Sardinian transducer] (and our [https://github.swarthmore.edu/Ling073-sp23/ling073-srd clone])
*Github repository for [https://github.com/apertium/apertium-eng English transducer]
*[https://www.limbasardasudsardigna.it/sar/images/Documenti/Didatica_e_Ainas/Ditzion%C3%A0riu%20Universale%20Rubattu.pdf Dictionary pdf]
*[http://ditzionariu.sardegnacultura.it/it/ Online official dictionary]
*[https://it.glosbe.com/sc/it Web-based machine translator]
*[http://vocabolariocasu.isresardegna.it/index.php?key=a&int=0&lemmi=cerca Sardinian-Italian web-based dictionary]
*[http://www.sardegnadigitallibrary.it/mmt/fullsize/2009050512495700047.pdf 1931 pdf with select translations]
*[https://onlinelibrary.wiley.com/doi/epdf/10.1111/j.0079-1636.2004.00130.x Definiteness effects: evidence from Sardinian]
*[https://www.icongrouponline.com/en/Detail/dictionary/049783698X/Webster%27s+Sardinian+-+English+Thesaurus+Dictionary: Webster's Sardinian English Thesaurus Dictionary]
*[https://www.academia.edu/15320922/Dizionario_della_lingua_Sarda_Vol_2 Italian-Sardinian Dictionary]
*[https://archive.org/details/vocabolariosardo00spanuoft/page/n361/mode/2up Old but extensive Sardo-Italian and vice versa dictionary]
*[https://limbasardasudsardigna.it/sar/images/Documenti/Didatica_e_Ainas/Vocabolariu_Sardu_Italianu_Spano.pdf nice Sardo-Italiano dictionary pdf]
*[http://www.fontesarda.it/sr/sr0045.htm Conjugations of "to have" in Sardinian]
*[https://sinnainotizie.com/2015/03/07/lezioni-di-grammatica-sardo-campidanese-undicesima-lezione-su-verbu-ai-aere/ Whole Sardinian grammar page about conjugations of to have all written in Sardinian language!]
*Sardinian grammar:[https://www.limbasardasudsardigna.it/sar/images/Documenti/Didatica_e_Ainas/grammatiga_sardo%20campidanese%20A.LEPORI.pdf pdf]
[[Category:Sp23_TranslationPairs]],[[Category:Sardinian]],[[Category:English]]

Sardinian and English

2023-05-04T16:34:24Z

Rorlija1: /* Final evaluation */

=Resources for Machine Translation from Sardinian to English=

==Developed Resources==
*[https://github.swarthmore.edu/Ling073-sp23/ling073-srd-eng-corpus Parallel corpus git repo].
*:Lines 1-8 from [http://maxia-mail.doomby.com/ this website].
*[https://github.swarthmore.edu/Ling073-sp23/ling073-srd-eng Git repo for language pair]
*[https://github.swarthmore.edu/Ling073-sp23/ling073-srd Git repo for Sardinian]
*[https://github.com/apertium/apertium-eng Forked git repo for English]
*[https://wikis.swarthmore.edu/ling073/Sardinian_and_English/Lexical_selection#srd_.E2.86.92_eng Lexical selection wiki]
*[https://wikis.swarthmore.edu/ling073/Sardinian_and_English/Contrastive_Grammar#Differences_in_parse_and_corresponding_examples Contrastive grammar wiki]
*[https://wikis.swarthmore.edu/ling073/Sardinian_and_English/Structural_transfer Structural transfer wiki]

==srd → eng evaluation==
*coverage of monolingual Sardinian transducer on srd.sentences.txt:
Number of tokenised words in the corpus: 262
Coverage: 94.66%
*coverage of bilingual transducer on srd.sentences
Number of tokenised words in the corpus: 266
Coverage: 85.71%

==Additions for polished RBMT system==
*Over 100 new stems to bilingual dictionary
*:(now we have 172 total entries in the .dix file)
*4 sets of lexical selection rules
*:(now we have rules that solve 5 problems in total)
*3 items from contrastive grammar implemented in transfer rules
*:(now we have rules that implement 4 total items)

==Final evaluation==
* For the monolingual transducer:
** Updated precision and recall against the (updated) <code>eval.test</code> and <code>eval.gold</code> files
** Coverage over the <code>large</code> corpus,
** The number of words in the <code>large</code> corpus,
** The number of stems in the transducer.
* For MT in the direction we developed (<code>srd-eng</code>):
** WER and PER over <code>longer</code> corpus.
** The proportion of stems translated correctly in the <code>longer</code> corpus.
** Trimmed coverage over <code>longer</code> and <code>large</code> corpora.
** The number of tokens in <code>longer</code> and <code>large</code> corpora.

==10 sentences glosses and outputs==
*Note: '''These are outputs at end of lexical transfer before lexical selection and other weeks' improvements were implemented'''
{| cellpadding=5
|Sardinian sentence || intended English translation || output of srd-eng-biltrans (lexical transfer) mode || output of srd-eng (full translation) mode
|-
|1) Su sardu est una limba antica. || Sardinian is an ancient language. || ^Su<det><def><m><sg>/The<det><def><m><sg>$ ^sardu<n><m><sg>/Sardinian<n><sg>$ ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$ ^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$^.<sent>/.<sent>$^.<sent>/.<sent>$
|| #The Sardinian #be #a language #ancient
|-
|2) Pro bider s'artìculu sighire custu culligamentu. || To read the article click on this link. || ^Pro<pr>/For<pr>/To<pr>$ ^bider<vblex><inf>/read<vblex><inf>$ ^su<det><def><mf><sg>/the<det><def><mf><sg>$ ^artìculu<n><m><sg>/article<n><sg>$ ^sighire<vblex><inf>/click<vblex><inf>$ ^custu<det><dem><m><sg>/this<det><m><sg>$ ^culligamentu<n><m><sg>/link<n><sg>$^.<sent>/.<sent>$^.<sent>/.<sent>$<m><sg>$ ^culligamentu<n><m><sg>/link<n><sg>$^.<sent>/.<sent>$^.<sent>/.<sent>$
|| For read #the article click #this link.
|-
|3) Su trenu sinke fit andande. || The train was leaving. || ^Su<det><def><m><sg>/The<det><def><m><sg>$ ^trenu<n><m><sg>/train<n><sg>$ ^sinke<cnjadv>/$ ^èssere<vbser><pii><p3><sg>/be<vbser><pii><p3><sg>$ ^andare<vblex><ger>/leave<vblex><ger>/go<vblex><ger>$^.<sent>/.<sent>$^.<sent>/.<sent>$

|| #The train #be leaving.
|-
|4) Su trenu at a arrivare a sas deke. || The train will arrive at ten. || ^Su<det><def><m><sg>/The<det><def><m><sg>$ ^trenu<n><m><sg>/train<n><sg>$ ^àere<vbhaver><pri><p3><sg>/have<vbhaver><pri><p3><sg>$ ^a<pr>/at<pr>/on<pr>/to<pr>$ ^arrivare<vblex><inf>/arrive<vblex><inf>$ ^a<pr>/at<pr>/on<pr>/to<pr>$ ^su<det><def><f><pl>/the<det><def><f><pl>$ ^deke<num><mf><sp>/ten<num><mf><sp>$^.<sent>/.<sent>$^.<sent>/.<sent>$
|| #The train #have at arrive at #the #ten.
|-
|5) Su trenu devet arrivare a sas deke. || The train should arrive at ten. || ^Su<det><def><m><sg>/The<det><def><m><sg>$ ^trenu<n><m><sg>/train<n><sg>$ ^dèvere<vblex><pri><p3><sg>/shall<vbmod><pri><p3><sg>$ ^arrivare<vblex><inf>/arrive<vblex><inf>$ ^a<pr>/at<pr>/on<pr>/to<pr>$ ^su<det><def><f><pl>/the<det><def><f><pl>$ ^deke<num><mf><sp>/ten<num><mf><sp>$^.<sent>/.<sent>$^.<sent>/.<sent>$
|| #The train #shall arrive at #the #ten.
|-
|6) T'appo natu ki su trenu devíat arrivare a sas deke. || I told you that the train would arrive at ten. || ^Ti<prn><pro><p2><mf><sg>/You<prn><pro><p2><mf><sg>$ ^àere<vbhaver><pri><p1><sg>/have<vbhaver><pri><p1><sg>$ ^nàrrere<vblex><pp><m><sg>/tell<vblex><pp><m><sg>$ ^chi<cnjsub>/that<cnjsub>$ ^su<det><def><m><sg>/the<det><def><m><sg>$ ^trenu<n><m><sg>/train<n><sg>$ ^dèvere<vblex><pii><p3><sg>/shall<vbmod><pii><p3><sg>$ ^arrivare<vblex><inf>/arrive<vblex><inf>$ ^a<pr>/at<pr>/on<pr>/to<pr>$ ^su<det><def><f><pl>/the<det><def><f><pl>$ ^deke<num><mf><sp>/ten<num><mf><sp>$^.<sent>/.<sent>$^.<sent>/.<sent>$
|| #You #have #tell that #the train #shall arrive at #the #ten.
|-
|7) No'isco si at a pròere cras. || I do not know if it will rain tomorrow. || ^No<adv>/Not<adv>$'^iscoare<vblex><pri><p1><sg>/know<vblex><pri><p1><sg>$ ^si<cnjsub>/if<cnjsub>$ ^àere<vbhaver><pri><p3><sg>/have<vbhaver><pri><p3><sg>$ ^a<pr>/at<pr>/on<pr>/to<pr>$ ^pròere<vblex><inf>/rain<vblex><inf>$ ^cras<adv>/tomorrow<adv>$^.<sent>/.<sent>$
|| Not'#know if #have at rain tomorrow

|-
|8) Una de sas berbekes est maláida. || One of the sheep is sick. || ^Unu<num><f><sp>/One<num><f><sp>$ ^de<pr>/to<pr>/of<pr>$ ^su<det><def><f><pl>/the<det><def><f><pl>$ ^berbeke<n><f><pl>/sheep<n><pl>$ ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$ ^malàidu<adj><f><sg>/sick<adj><f><sg>$^.<sent>/.<sent>$
|| #One to #the sheep #be #sick

|-
|9) Appo pèrditu duos de sos libros meos. || I have lost two of my books. || ^Àere<vbhaver><pri><p1><sg>/Have<vbhaver><pri><p1><sg>$ ^pèrdere<vblex><pp><m><sg>/lose<vblex><pp><m><sg>$ ^duos<num><m><sp>/two<num><m><sp>$ ^de<pr>/to<pr>/of<pr>$ ^su<det><def><m><pl>/the<det><def><m><pl>$ ^libru<n><m><pl>/book<n><pl>$ ^meu<prn><pos><m><pl>/my<prn><pos><m><pl>$^.<sent>/.<sent>$

|| #Have #lose #two to #the books #my

|-
|10) M'an natu ki su trenu devíat arrivare a sas nove. || They told me that the train was supposed to arrive at nine. || ^Mi<prn><pro><p1><mf><sg>/I<prn><pro><p1><mf><sg>$ ^àere<vbhaver><pri><p3><pl>/have<vbhaver><pri><p3><pl>$ ^nàrrere<vblex><pp><m><sg>/tell<vblex><pp><m><sg>$ ^chi<cnjsub>/that<cnjsub>$ ^su<det><def><m><sg>/the<det><def><m><sg>$ ^trenu<n><m><sg>/train<n><sg>$ ^dèvere<vblex><pii><p3><sg>/shall<vbmod><pii><p3><sg>$ ^arrivare<vblex><inf>/arrive<vblex><inf>$ ^a<pr>/at<pr>/on<pr>/to<pr>$ ^su<det><def><f><pl>/the<det><def><f><pl>$ ^nove<num><mf><sp>/nine<num><mf><sp>$^.<sent>/.<sent>$
|| #I #have #tell that #the train #shall arrive at #the #nine
|
|}

==expanding lexicon==

{| cellpadding=5
|medas || many || <adj>
|-https://wikis.swarthmore.edu/ling073/index.php?title=Sardinian_and_English&action=edit
|piseddas || girls || <n><pl>
|-
|sun || they are || <v>
|-
|bennidas || to come (home) || <v><pp><fpl>
|-
|balladu || to dance || <v><pp>
|-
|cantaiat || to sing || <v><sg3>
|-
|sos/sa || the || <det>
|-
|piattos || plates || <n><pl>
|-
|mesa || table || <n><sg>
|-
|bi/b' || N/A || <cl>
|-
|problemas || problems || <n><pl>
|-
|unu || one/a || <adj>/<det>
|-
|ube || where || <adv>
|-
|mortu || dead || <v><pp>
|-
|sordatos || soldiers || <n><pl>
|-
|tenimus || we have || <v><pl1>
|-
|frores || flowers || <n><pl>
|-
|keret || to be necessary || <v><sg3>
|-
|mancat || to be missing || <v><sg3>
|-
|ovos || eggs || <n><pl>
|-
|danca || meadow || <n>
|-
|ortu || orchard || <n>
|-
|frade || brother || <n>
|-
|fizza || daughter || <n>
|-
|re || king || <n>
|-
|ora || hour || <n>
|-
|subra || above/on || <prep>
|-
|a || to/at || <prep>
|-
|cumintzos || origins || <n><pl>
|-
|e || and || <conj>
|-
|andamentu || evolution || <n>
|-
|istòricu || historical || <adj>
|-
|de || of/to || <prep>
|-
|sa || the || <det>
|-
|poesia || poetry || <n>
|-
|a bolu || improvised || <adj> (a bolu = improvised, on the fly)
|-
|in || in || <prep>
|-
|sardu || Sardinian || <n>
|-
|logudoresu || Logudorese || <adj>
|-
|non || not || <adv>
|-
|ischit || known || <v><pp>
|-
|meda || much || <adv>
|-
|custu || this || <det><prox>
|-
|artìculu || article || <n>
|-
|chircat || tries || <v><sg3>
|-
|bogare || to bring out || <v>
|-
|pizu || surface || <n> (bogare a pizu = to shed light on, to bring to the surface; see complicated translations of bogare: [http://vocabolariocasu.isresardegna.it/index.php?key=b&int=0&lemmi=cerca&codice=b1264000 here])
|-
|ammentos || memories || <n><pl>
|-
|ammentu || memory || <n>
|-
|ammentare || to remember || <v>
|-
|documentados || documented || <adj>
|-
|si || [null] || <> -- reflexive
|-
|primas || first || <adj>
|-
|disputas || competitions || <n><pl>
|-
|primas || first || <adj>
|-
|tra || between || <prep>
|-
|poetes || poets || <n><pl>
|-
|cale || which || <prn><rel>
|-
|esserent || were || <v> past imperfect 3rd person plural
|-
|règulas || rules, modalities || <n><pl>
|-
|su || the || <det>
|-
|cunfruntu || confrontation || <n>
|-
|sende || being || <v><ger>
|-
|una || a/one || <art>/<adj>
|-
|chirca || research || <n>
|-
|andera || ongoing/progressive || <adj>
|-
|testu || text || <n>
|-
|diat || [null] || <subj><sg3>
|-
|poder || to be able to || <v><inf>
|-
|aer || to have || <v><inf> (also hàere or àere)
|-
|mudonzos || modifications || <n><pl>
|-
|mudonzos || modifications || <n><pl>
|-
|novas || new || <adj><pl>
|-
|noas || data || <n><pl>
|-
|Pro || to || <prep> <-- keep this in mind for lexical selection (to)
|-
|bider || to read || <v><inf>
|-
|artìculu || article || <n>
|-
|sighire || click on || <v><inf>
|-
|intrare || enter || <v><inf>
|-
|desizadu || desired || <adj>
|-
|trenu || train || <n>
|-
|sinke || [null] || <foc>
|-
|fit || was || <v><imp><sg3>
|-
|andande || leaving || <v><ger>
|-
|at || it will || <>
|-
|sas || the || <det>
|-
|deke || ten || <n>
|-
|devet || should || <adv>
|-
|deke || ten || <adj>
|-
|appo || I have || <v><sg1>
|-
|natu || told || <v><pp>
|-
|próere || to rain || <v><inf>
|-
|arrivare || to arrive || <v><inf>
|-
|isco || I know || <v><sg1>
|-
|si || if || <conj>
|-
|ki || that || <conj>
|-
|cras || tomorrow || <adv>
|-
|meos || my || <pos>
|-
|andatos || gone || <adj><pl>
|
|}

===glosses===

Cando so arrivatu a s'istazione, su trenu sink'andaiat

'when I arrived at the station, the train was leaving'

Su trenu sinke fit andande

'The train was leaving"

Su trenu at a arrivare a sas deke

'The train will arrive at ten o'clock'

Su trenu devet arrivare a sas deke

'The train is supposed to arrive at ten o'clock'

T'appo natu ki su trenu diat arrivare a sas deke

'I told you that the train would arrive at ten o'clock'

M'an natu ki su trenu devíat arrivare a sas nove

'They told me that the train was supposed to arrive at nine'

At a próere cras

'It will rain tomorrow'

Devet próere cras

'it is supposed to rain tomorrow'

At a próere cras? Si emmo abbarramus in domo, ma su nono andamus a mare

'Will it rain tomorrow? If so we shall stay at homr, buy if not we will go to the sea'

No'isco si at a próere cras

'I do to know whether it will rain tomorrow'

Una de sas berbekes est maláida

'one of the sheep is sick'

Appo pèrditu duos de sos libros meos

'I have lost two of my books'

Metas de custas pitzinnas sun galanas

'Many of these girls are pretty'

Una pitzinna meta bella

'a very beautiful girl'

Cussas duas bravas pitzinnas

'those two good girls'

unu better cane bellu

'a huge beautiful dog'

un'átteru bette cane

'another huge dog'

Sun andatos a Frantza

'they went to France'

Est ghiratu dae Corsica

'He returned from Corsica'

Connnosco bene sa Frantza

"i know France well'

Custu libru est iscrittu in tedescu

'This book is written in German'

Cussus paráula venit dae su catalanu

'This word comes from Catalan'

Su sardu est una limba antica

'Sardinian is an ancient language'

Appo mandicatu casu

'I ate cheese'

Laura est toddende frores

'Laura is picking flowers'

De frores non nd'appo tódditu

'I did not pick any flowers'

No'amus comporatu pane

'We did not buy bread'

Mandico sa pasta kin casu

'I ate pasta with cheese'

Tres sórrikes an mandicatu tottu su casu

'Three mice ate all the cheese'

semus ponnende vinu in ampullas

'We are putting wine in bottles'

lettu meu esr

'It is my bed'

No'appo lessu libru perunu

'i did not read any book'

Sos k'an furatu si dinari at a èssere punitos

'The people who stole the money will be punished'

Appo invitat sos de Juanne

'I invited Jon's family'

Cussa pinna est sa mea

'That pen is mine'

Cudda mákkina est sa de Juanne

'That car is John's'

Custa ricca at datu mili francos a su vetzu

'This rich woman gave a thousand lira to the old man'

Su guvernu devíat dare ua pensione a dondzi vetzu

'The government should give a pension to every old person'

==External Resources==

*Github repository for [https://github.com/apertium/apertium-srd Sardinian transducer] (and our [https://github.swarthmore.edu/Ling073-sp23/ling073-srd clone])
*Github repository for [https://github.com/apertium/apertium-eng English transducer]
*[https://www.limbasardasudsardigna.it/sar/images/Documenti/Didatica_e_Ainas/Ditzion%C3%A0riu%20Universale%20Rubattu.pdf Dictionary pdf]
*[http://ditzionariu.sardegnacultura.it/it/ Online official dictionary]
*[https://it.glosbe.com/sc/it Web-based machine translator]
*[http://vocabolariocasu.isresardegna.it/index.php?key=a&int=0&lemmi=cerca Sardinian-Italian web-based dictionary]
*[http://www.sardegnadigitallibrary.it/mmt/fullsize/2009050512495700047.pdf 1931 pdf with select translations]
*[https://onlinelibrary.wiley.com/doi/epdf/10.1111/j.0079-1636.2004.00130.x Definiteness effects: evidence from Sardinian]
*[https://www.icongrouponline.com/en/Detail/dictionary/049783698X/Webster%27s+Sardinian+-+English+Thesaurus+Dictionary: Webster's Sardinian English Thesaurus Dictionary]
*[https://www.academia.edu/15320922/Dizionario_della_lingua_Sarda_Vol_2 Italian-Sardinian Dictionary]
*[https://archive.org/details/vocabolariosardo00spanuoft/page/n361/mode/2up Old but extensive Sardo-Italian and vice versa dictionary]
*[https://limbasardasudsardigna.it/sar/images/Documenti/Didatica_e_Ainas/Vocabolariu_Sardu_Italianu_Spano.pdf nice Sardo-Italiano dictionary pdf]
*[http://www.fontesarda.it/sr/sr0045.htm Conjugations of "to have" in Sardinian]
*[https://sinnainotizie.com/2015/03/07/lezioni-di-grammatica-sardo-campidanese-undicesima-lezione-su-verbu-ai-aere/ Whole Sardinian grammar page about conjugations of to have all written in Sardinian language!]
*Sardinian grammar:[https://www.limbasardasudsardigna.it/sar/images/Documenti/Didatica_e_Ainas/grammatiga_sardo%20campidanese%20A.LEPORI.pdf pdf]
[[Category:Sp23_TranslationPairs]],[[Category:Sardinian]],[[Category:English]]

Sardinian and English

2023-05-04T16:34:03Z

Rorlija1: /* Final evaluation */

=Resources for Machine Translation from Sardinian to English=

==Developed Resources==
*[https://github.swarthmore.edu/Ling073-sp23/ling073-srd-eng-corpus Parallel corpus git repo].
*:Lines 1-8 from [http://maxia-mail.doomby.com/ this website].
*[https://github.swarthmore.edu/Ling073-sp23/ling073-srd-eng Git repo for language pair]
*[https://github.swarthmore.edu/Ling073-sp23/ling073-srd Git repo for Sardinian]
*[https://github.com/apertium/apertium-eng Forked git repo for English]
*[https://wikis.swarthmore.edu/ling073/Sardinian_and_English/Lexical_selection#srd_.E2.86.92_eng Lexical selection wiki]
*[https://wikis.swarthmore.edu/ling073/Sardinian_and_English/Contrastive_Grammar#Differences_in_parse_and_corresponding_examples Contrastive grammar wiki]
*[https://wikis.swarthmore.edu/ling073/Sardinian_and_English/Structural_transfer Structural transfer wiki]

==srd → eng evaluation==
*coverage of monolingual Sardinian transducer on srd.sentences.txt:
Number of tokenised words in the corpus: 262
Coverage: 94.66%
*coverage of bilingual transducer on srd.sentences
Number of tokenised words in the corpus: 266
Coverage: 85.71%

==Additions for polished RBMT system==
*Over 100 new stems to bilingual dictionary
*:(now we have 172 total entries in the .dix file)
*4 sets of lexical selection rules
*:(now we have rules that solve 5 problems in total)
*3 items from contrastive grammar implemented in transfer rules
*:(now we have rules that implement 4 total items)

==Final evaluation==
* For your monolingual transducer:
** Updated precision and recall against the (updated) <code>eval.test</code> and <code>eval.gold</code> files
** Coverage over the <code>large</code> corpus,
** The number of words in the <code>large</code> corpus,
** The number of stems in the transducer.
* For MT in the direction we developed (<code>srd-eng</code>):
** WER and PER over <code>longer</code> corpus.
** The proportion of stems translated correctly in the <code>longer</code> corpus.
** Trimmed coverage over <code>longer</code> and <code>large</code> corpora.
** The number of tokens in <code>longer</code> and <code>large</code> corpora.

==10 sentences glosses and outputs==
*Note: '''These are outputs at end of lexical transfer before lexical selection and other weeks' improvements were implemented'''
{| cellpadding=5
|Sardinian sentence || intended English translation || output of srd-eng-biltrans (lexical transfer) mode || output of srd-eng (full translation) mode
|-
|1) Su sardu est una limba antica. || Sardinian is an ancient language. || ^Su<det><def><m><sg>/The<det><def><m><sg>$ ^sardu<n><m><sg>/Sardinian<n><sg>$ ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$ ^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$^.<sent>/.<sent>$^.<sent>/.<sent>$
|| #The Sardinian #be #a language #ancient
|-
|2) Pro bider s'artìculu sighire custu culligamentu. || To read the article click on this link. || ^Pro<pr>/For<pr>/To<pr>$ ^bider<vblex><inf>/read<vblex><inf>$ ^su<det><def><mf><sg>/the<det><def><mf><sg>$ ^artìculu<n><m><sg>/article<n><sg>$ ^sighire<vblex><inf>/click<vblex><inf>$ ^custu<det><dem><m><sg>/this<det><m><sg>$ ^culligamentu<n><m><sg>/link<n><sg>$^.<sent>/.<sent>$^.<sent>/.<sent>$<m><sg>$ ^culligamentu<n><m><sg>/link<n><sg>$^.<sent>/.<sent>$^.<sent>/.<sent>$
|| For read #the article click #this link.
|-
|3) Su trenu sinke fit andande. || The train was leaving. || ^Su<det><def><m><sg>/The<det><def><m><sg>$ ^trenu<n><m><sg>/train<n><sg>$ ^sinke<cnjadv>/$ ^èssere<vbser><pii><p3><sg>/be<vbser><pii><p3><sg>$ ^andare<vblex><ger>/leave<vblex><ger>/go<vblex><ger>$^.<sent>/.<sent>$^.<sent>/.<sent>$

|| #The train #be leaving.
|-
|4) Su trenu at a arrivare a sas deke. || The train will arrive at ten. || ^Su<det><def><m><sg>/The<det><def><m><sg>$ ^trenu<n><m><sg>/train<n><sg>$ ^àere<vbhaver><pri><p3><sg>/have<vbhaver><pri><p3><sg>$ ^a<pr>/at<pr>/on<pr>/to<pr>$ ^arrivare<vblex><inf>/arrive<vblex><inf>$ ^a<pr>/at<pr>/on<pr>/to<pr>$ ^su<det><def><f><pl>/the<det><def><f><pl>$ ^deke<num><mf><sp>/ten<num><mf><sp>$^.<sent>/.<sent>$^.<sent>/.<sent>$
|| #The train #have at arrive at #the #ten.
|-
|5) Su trenu devet arrivare a sas deke. || The train should arrive at ten. || ^Su<det><def><m><sg>/The<det><def><m><sg>$ ^trenu<n><m><sg>/train<n><sg>$ ^dèvere<vblex><pri><p3><sg>/shall<vbmod><pri><p3><sg>$ ^arrivare<vblex><inf>/arrive<vblex><inf>$ ^a<pr>/at<pr>/on<pr>/to<pr>$ ^su<det><def><f><pl>/the<det><def><f><pl>$ ^deke<num><mf><sp>/ten<num><mf><sp>$^.<sent>/.<sent>$^.<sent>/.<sent>$
|| #The train #shall arrive at #the #ten.
|-
|6) T'appo natu ki su trenu devíat arrivare a sas deke. || I told you that the train would arrive at ten. || ^Ti<prn><pro><p2><mf><sg>/You<prn><pro><p2><mf><sg>$ ^àere<vbhaver><pri><p1><sg>/have<vbhaver><pri><p1><sg>$ ^nàrrere<vblex><pp><m><sg>/tell<vblex><pp><m><sg>$ ^chi<cnjsub>/that<cnjsub>$ ^su<det><def><m><sg>/the<det><def><m><sg>$ ^trenu<n><m><sg>/train<n><sg>$ ^dèvere<vblex><pii><p3><sg>/shall<vbmod><pii><p3><sg>$ ^arrivare<vblex><inf>/arrive<vblex><inf>$ ^a<pr>/at<pr>/on<pr>/to<pr>$ ^su<det><def><f><pl>/the<det><def><f><pl>$ ^deke<num><mf><sp>/ten<num><mf><sp>$^.<sent>/.<sent>$^.<sent>/.<sent>$
|| #You #have #tell that #the train #shall arrive at #the #ten.
|-
|7) No'isco si at a pròere cras. || I do not know if it will rain tomorrow. || ^No<adv>/Not<adv>$'^iscoare<vblex><pri><p1><sg>/know<vblex><pri><p1><sg>$ ^si<cnjsub>/if<cnjsub>$ ^àere<vbhaver><pri><p3><sg>/have<vbhaver><pri><p3><sg>$ ^a<pr>/at<pr>/on<pr>/to<pr>$ ^pròere<vblex><inf>/rain<vblex><inf>$ ^cras<adv>/tomorrow<adv>$^.<sent>/.<sent>$
|| Not'#know if #have at rain tomorrow

|-
|8) Una de sas berbekes est maláida. || One of the sheep is sick. || ^Unu<num><f><sp>/One<num><f><sp>$ ^de<pr>/to<pr>/of<pr>$ ^su<det><def><f><pl>/the<det><def><f><pl>$ ^berbeke<n><f><pl>/sheep<n><pl>$ ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$ ^malàidu<adj><f><sg>/sick<adj><f><sg>$^.<sent>/.<sent>$
|| #One to #the sheep #be #sick

|-
|9) Appo pèrditu duos de sos libros meos. || I have lost two of my books. || ^Àere<vbhaver><pri><p1><sg>/Have<vbhaver><pri><p1><sg>$ ^pèrdere<vblex><pp><m><sg>/lose<vblex><pp><m><sg>$ ^duos<num><m><sp>/two<num><m><sp>$ ^de<pr>/to<pr>/of<pr>$ ^su<det><def><m><pl>/the<det><def><m><pl>$ ^libru<n><m><pl>/book<n><pl>$ ^meu<prn><pos><m><pl>/my<prn><pos><m><pl>$^.<sent>/.<sent>$

|| #Have #lose #two to #the books #my

|-
|10) M'an natu ki su trenu devíat arrivare a sas nove. || They told me that the train was supposed to arrive at nine. || ^Mi<prn><pro><p1><mf><sg>/I<prn><pro><p1><mf><sg>$ ^àere<vbhaver><pri><p3><pl>/have<vbhaver><pri><p3><pl>$ ^nàrrere<vblex><pp><m><sg>/tell<vblex><pp><m><sg>$ ^chi<cnjsub>/that<cnjsub>$ ^su<det><def><m><sg>/the<det><def><m><sg>$ ^trenu<n><m><sg>/train<n><sg>$ ^dèvere<vblex><pii><p3><sg>/shall<vbmod><pii><p3><sg>$ ^arrivare<vblex><inf>/arrive<vblex><inf>$ ^a<pr>/at<pr>/on<pr>/to<pr>$ ^su<det><def><f><pl>/the<det><def><f><pl>$ ^nove<num><mf><sp>/nine<num><mf><sp>$^.<sent>/.<sent>$
|| #I #have #tell that #the train #shall arrive at #the #nine
|
|}

==expanding lexicon==

{| cellpadding=5
|medas || many || <adj>
|-https://wikis.swarthmore.edu/ling073/index.php?title=Sardinian_and_English&action=edit
|piseddas || girls || <n><pl>
|-
|sun || they are || <v>
|-
|bennidas || to come (home) || <v><pp><fpl>
|-
|balladu || to dance || <v><pp>
|-
|cantaiat || to sing || <v><sg3>
|-
|sos/sa || the || <det>
|-
|piattos || plates || <n><pl>
|-
|mesa || table || <n><sg>
|-
|bi/b' || N/A || <cl>
|-
|problemas || problems || <n><pl>
|-
|unu || one/a || <adj>/<det>
|-
|ube || where || <adv>
|-
|mortu || dead || <v><pp>
|-
|sordatos || soldiers || <n><pl>
|-
|tenimus || we have || <v><pl1>
|-
|frores || flowers || <n><pl>
|-
|keret || to be necessary || <v><sg3>
|-
|mancat || to be missing || <v><sg3>
|-
|ovos || eggs || <n><pl>
|-
|danca || meadow || <n>
|-
|ortu || orchard || <n>
|-
|frade || brother || <n>
|-
|fizza || daughter || <n>
|-
|re || king || <n>
|-
|ora || hour || <n>
|-
|subra || above/on || <prep>
|-
|a || to/at || <prep>
|-
|cumintzos || origins || <n><pl>
|-
|e || and || <conj>
|-
|andamentu || evolution || <n>
|-
|istòricu || historical || <adj>
|-
|de || of/to || <prep>
|-
|sa || the || <det>
|-
|poesia || poetry || <n>
|-
|a bolu || improvised || <adj> (a bolu = improvised, on the fly)
|-
|in || in || <prep>
|-
|sardu || Sardinian || <n>
|-
|logudoresu || Logudorese || <adj>
|-
|non || not || <adv>
|-
|ischit || known || <v><pp>
|-
|meda || much || <adv>
|-
|custu || this || <det><prox>
|-
|artìculu || article || <n>
|-
|chircat || tries || <v><sg3>
|-
|bogare || to bring out || <v>
|-
|pizu || surface || <n> (bogare a pizu = to shed light on, to bring to the surface; see complicated translations of bogare: [http://vocabolariocasu.isresardegna.it/index.php?key=b&int=0&lemmi=cerca&codice=b1264000 here])
|-
|ammentos || memories || <n><pl>
|-
|ammentu || memory || <n>
|-
|ammentare || to remember || <v>
|-
|documentados || documented || <adj>
|-
|si || [null] || <> -- reflexive
|-
|primas || first || <adj>
|-
|disputas || competitions || <n><pl>
|-
|primas || first || <adj>
|-
|tra || between || <prep>
|-
|poetes || poets || <n><pl>
|-
|cale || which || <prn><rel>
|-
|esserent || were || <v> past imperfect 3rd person plural
|-
|règulas || rules, modalities || <n><pl>
|-
|su || the || <det>
|-
|cunfruntu || confrontation || <n>
|-
|sende || being || <v><ger>
|-
|una || a/one || <art>/<adj>
|-
|chirca || research || <n>
|-
|andera || ongoing/progressive || <adj>
|-
|testu || text || <n>
|-
|diat || [null] || <subj><sg3>
|-
|poder || to be able to || <v><inf>
|-
|aer || to have || <v><inf> (also hàere or àere)
|-
|mudonzos || modifications || <n><pl>
|-
|mudonzos || modifications || <n><pl>
|-
|novas || new || <adj><pl>
|-
|noas || data || <n><pl>
|-
|Pro || to || <prep> <-- keep this in mind for lexical selection (to)
|-
|bider || to read || <v><inf>
|-
|artìculu || article || <n>
|-
|sighire || click on || <v><inf>
|-
|intrare || enter || <v><inf>
|-
|desizadu || desired || <adj>
|-
|trenu || train || <n>
|-
|sinke || [null] || <foc>
|-
|fit || was || <v><imp><sg3>
|-
|andande || leaving || <v><ger>
|-
|at || it will || <>
|-
|sas || the || <det>
|-
|deke || ten || <n>
|-
|devet || should || <adv>
|-
|deke || ten || <adj>
|-
|appo || I have || <v><sg1>
|-
|natu || told || <v><pp>
|-
|próere || to rain || <v><inf>
|-
|arrivare || to arrive || <v><inf>
|-
|isco || I know || <v><sg1>
|-
|si || if || <conj>
|-
|ki || that || <conj>
|-
|cras || tomorrow || <adv>
|-
|meos || my || <pos>
|-
|andatos || gone || <adj><pl>
|
|}

===glosses===

Cando so arrivatu a s'istazione, su trenu sink'andaiat

'when I arrived at the station, the train was leaving'

Su trenu sinke fit andande

'The train was leaving"

Su trenu at a arrivare a sas deke

'The train will arrive at ten o'clock'

Su trenu devet arrivare a sas deke

'The train is supposed to arrive at ten o'clock'

T'appo natu ki su trenu diat arrivare a sas deke

'I told you that the train would arrive at ten o'clock'

M'an natu ki su trenu devíat arrivare a sas nove

'They told me that the train was supposed to arrive at nine'

At a próere cras

'It will rain tomorrow'

Devet próere cras

'it is supposed to rain tomorrow'

At a próere cras? Si emmo abbarramus in domo, ma su nono andamus a mare

'Will it rain tomorrow? If so we shall stay at homr, buy if not we will go to the sea'

No'isco si at a próere cras

'I do to know whether it will rain tomorrow'

Una de sas berbekes est maláida

'one of the sheep is sick'

Appo pèrditu duos de sos libros meos

'I have lost two of my books'

Metas de custas pitzinnas sun galanas

'Many of these girls are pretty'

Una pitzinna meta bella

'a very beautiful girl'

Cussas duas bravas pitzinnas

'those two good girls'

unu better cane bellu

'a huge beautiful dog'

un'átteru bette cane

'another huge dog'

Sun andatos a Frantza

'they went to France'

Est ghiratu dae Corsica

'He returned from Corsica'

Connnosco bene sa Frantza

"i know France well'

Custu libru est iscrittu in tedescu

'This book is written in German'

Cussus paráula venit dae su catalanu

'This word comes from Catalan'

Su sardu est una limba antica

'Sardinian is an ancient language'

Appo mandicatu casu

'I ate cheese'

Laura est toddende frores

'Laura is picking flowers'

De frores non nd'appo tódditu

'I did not pick any flowers'

No'amus comporatu pane

'We did not buy bread'

Mandico sa pasta kin casu

'I ate pasta with cheese'

Tres sórrikes an mandicatu tottu su casu

'Three mice ate all the cheese'

semus ponnende vinu in ampullas

'We are putting wine in bottles'

lettu meu esr

'It is my bed'

No'appo lessu libru perunu

'i did not read any book'

Sos k'an furatu si dinari at a èssere punitos

'The people who stole the money will be punished'

Appo invitat sos de Juanne

'I invited Jon's family'

Cussa pinna est sa mea

'That pen is mine'

Cudda mákkina est sa de Juanne

'That car is John's'

Custa ricca at datu mili francos a su vetzu

'This rich woman gave a thousand lira to the old man'

Su guvernu devíat dare ua pensione a dondzi vetzu

'The government should give a pension to every old person'

==External Resources==

*Github repository for [https://github.com/apertium/apertium-srd Sardinian transducer] (and our [https://github.swarthmore.edu/Ling073-sp23/ling073-srd clone])
*Github repository for [https://github.com/apertium/apertium-eng English transducer]
*[https://www.limbasardasudsardigna.it/sar/images/Documenti/Didatica_e_Ainas/Ditzion%C3%A0riu%20Universale%20Rubattu.pdf Dictionary pdf]
*[http://ditzionariu.sardegnacultura.it/it/ Online official dictionary]
*[https://it.glosbe.com/sc/it Web-based machine translator]
*[http://vocabolariocasu.isresardegna.it/index.php?key=a&int=0&lemmi=cerca Sardinian-Italian web-based dictionary]
*[http://www.sardegnadigitallibrary.it/mmt/fullsize/2009050512495700047.pdf 1931 pdf with select translations]
*[https://onlinelibrary.wiley.com/doi/epdf/10.1111/j.0079-1636.2004.00130.x Definiteness effects: evidence from Sardinian]
*[https://www.icongrouponline.com/en/Detail/dictionary/049783698X/Webster%27s+Sardinian+-+English+Thesaurus+Dictionary: Webster's Sardinian English Thesaurus Dictionary]
*[https://www.academia.edu/15320922/Dizionario_della_lingua_Sarda_Vol_2 Italian-Sardinian Dictionary]
*[https://archive.org/details/vocabolariosardo00spanuoft/page/n361/mode/2up Old but extensive Sardo-Italian and vice versa dictionary]
*[https://limbasardasudsardigna.it/sar/images/Documenti/Didatica_e_Ainas/Vocabolariu_Sardu_Italianu_Spano.pdf nice Sardo-Italiano dictionary pdf]
*[http://www.fontesarda.it/sr/sr0045.htm Conjugations of "to have" in Sardinian]
*[https://sinnainotizie.com/2015/03/07/lezioni-di-grammatica-sardo-campidanese-undicesima-lezione-su-verbu-ai-aere/ Whole Sardinian grammar page about conjugations of to have all written in Sardinian language!]
*Sardinian grammar:[https://www.limbasardasudsardigna.it/sar/images/Documenti/Didatica_e_Ainas/grammatiga_sardo%20campidanese%20A.LEPORI.pdf pdf]
[[Category:Sp23_TranslationPairs]],[[Category:Sardinian]],[[Category:English]]

Sardinian and English

2023-05-04T16:33:45Z

Rorlija1: /* Final evaluation */

=Resources for Machine Translation from Sardinian to English=

==Developed Resources==
*[https://github.swarthmore.edu/Ling073-sp23/ling073-srd-eng-corpus Parallel corpus git repo].
*:Lines 1-8 from [http://maxia-mail.doomby.com/ this website].
*[https://github.swarthmore.edu/Ling073-sp23/ling073-srd-eng Git repo for language pair]
*[https://github.swarthmore.edu/Ling073-sp23/ling073-srd Git repo for Sardinian]
*[https://github.com/apertium/apertium-eng Forked git repo for English]
*[https://wikis.swarthmore.edu/ling073/Sardinian_and_English/Lexical_selection#srd_.E2.86.92_eng Lexical selection wiki]
*[https://wikis.swarthmore.edu/ling073/Sardinian_and_English/Contrastive_Grammar#Differences_in_parse_and_corresponding_examples Contrastive grammar wiki]
*[https://wikis.swarthmore.edu/ling073/Sardinian_and_English/Structural_transfer Structural transfer wiki]

==srd → eng evaluation==
*coverage of monolingual Sardinian transducer on srd.sentences.txt:
Number of tokenised words in the corpus: 262
Coverage: 94.66%
*coverage of bilingual transducer on srd.sentences
Number of tokenised words in the corpus: 266
Coverage: 85.71%

==Additions for polished RBMT system==
*Over 100 new stems to bilingual dictionary
*:(now we have 172 total entries in the .dix file)
*4 sets of lexical selection rules
*:(now we have rules that solve 5 problems in total)
*3 items from contrastive grammar implemented in transfer rules
*:(now we have rules that implement 4 total items)

==Final evaluation==
* For your monolingual transducer:
** Updated precision and recall against the (updated) <code>eval.test</code> and <code>eval.gold</code> files (see [[Midterm overview#Evaluating your transducer]]),
** Coverage over the <code>large</code> corpus,
** The number of words in the <code>large</code> corpus,
** The number of stems in the transducer.
* For MT in the direction we developed (<code>srd-eng</code>):
** WER and PER over <code>longer</code> corpus.
** The proportion of stems translated correctly in the <code>longer</code> corpus.
** Trimmed coverage over <code>longer</code> and <code>large</code> corpora.
** The number of tokens in <code>longer</code> and <code>large</code> corpora.

==10 sentences glosses and outputs==
*Note: '''These are outputs at end of lexical transfer before lexical selection and other weeks' improvements were implemented'''
{| cellpadding=5
|Sardinian sentence || intended English translation || output of srd-eng-biltrans (lexical transfer) mode || output of srd-eng (full translation) mode
|-
|1) Su sardu est una limba antica. || Sardinian is an ancient language. || ^Su<det><def><m><sg>/The<det><def><m><sg>$ ^sardu<n><m><sg>/Sardinian<n><sg>$ ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$ ^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$^.<sent>/.<sent>$^.<sent>/.<sent>$
|| #The Sardinian #be #a language #ancient
|-
|2) Pro bider s'artìculu sighire custu culligamentu. || To read the article click on this link. || ^Pro<pr>/For<pr>/To<pr>$ ^bider<vblex><inf>/read<vblex><inf>$ ^su<det><def><mf><sg>/the<det><def><mf><sg>$ ^artìculu<n><m><sg>/article<n><sg>$ ^sighire<vblex><inf>/click<vblex><inf>$ ^custu<det><dem><m><sg>/this<det><m><sg>$ ^culligamentu<n><m><sg>/link<n><sg>$^.<sent>/.<sent>$^.<sent>/.<sent>$<m><sg>$ ^culligamentu<n><m><sg>/link<n><sg>$^.<sent>/.<sent>$^.<sent>/.<sent>$
|| For read #the article click #this link.
|-
|3) Su trenu sinke fit andande. || The train was leaving. || ^Su<det><def><m><sg>/The<det><def><m><sg>$ ^trenu<n><m><sg>/train<n><sg>$ ^sinke<cnjadv>/$ ^èssere<vbser><pii><p3><sg>/be<vbser><pii><p3><sg>$ ^andare<vblex><ger>/leave<vblex><ger>/go<vblex><ger>$^.<sent>/.<sent>$^.<sent>/.<sent>$

|| #The train #be leaving.
|-
|4) Su trenu at a arrivare a sas deke. || The train will arrive at ten. || ^Su<det><def><m><sg>/The<det><def><m><sg>$ ^trenu<n><m><sg>/train<n><sg>$ ^àere<vbhaver><pri><p3><sg>/have<vbhaver><pri><p3><sg>$ ^a<pr>/at<pr>/on<pr>/to<pr>$ ^arrivare<vblex><inf>/arrive<vblex><inf>$ ^a<pr>/at<pr>/on<pr>/to<pr>$ ^su<det><def><f><pl>/the<det><def><f><pl>$ ^deke<num><mf><sp>/ten<num><mf><sp>$^.<sent>/.<sent>$^.<sent>/.<sent>$
|| #The train #have at arrive at #the #ten.
|-
|5) Su trenu devet arrivare a sas deke. || The train should arrive at ten. || ^Su<det><def><m><sg>/The<det><def><m><sg>$ ^trenu<n><m><sg>/train<n><sg>$ ^dèvere<vblex><pri><p3><sg>/shall<vbmod><pri><p3><sg>$ ^arrivare<vblex><inf>/arrive<vblex><inf>$ ^a<pr>/at<pr>/on<pr>/to<pr>$ ^su<det><def><f><pl>/the<det><def><f><pl>$ ^deke<num><mf><sp>/ten<num><mf><sp>$^.<sent>/.<sent>$^.<sent>/.<sent>$
|| #The train #shall arrive at #the #ten.
|-
|6) T'appo natu ki su trenu devíat arrivare a sas deke. || I told you that the train would arrive at ten. || ^Ti<prn><pro><p2><mf><sg>/You<prn><pro><p2><mf><sg>$ ^àere<vbhaver><pri><p1><sg>/have<vbhaver><pri><p1><sg>$ ^nàrrere<vblex><pp><m><sg>/tell<vblex><pp><m><sg>$ ^chi<cnjsub>/that<cnjsub>$ ^su<det><def><m><sg>/the<det><def><m><sg>$ ^trenu<n><m><sg>/train<n><sg>$ ^dèvere<vblex><pii><p3><sg>/shall<vbmod><pii><p3><sg>$ ^arrivare<vblex><inf>/arrive<vblex><inf>$ ^a<pr>/at<pr>/on<pr>/to<pr>$ ^su<det><def><f><pl>/the<det><def><f><pl>$ ^deke<num><mf><sp>/ten<num><mf><sp>$^.<sent>/.<sent>$^.<sent>/.<sent>$
|| #You #have #tell that #the train #shall arrive at #the #ten.
|-
|7) No'isco si at a pròere cras. || I do not know if it will rain tomorrow. || ^No<adv>/Not<adv>$'^iscoare<vblex><pri><p1><sg>/know<vblex><pri><p1><sg>$ ^si<cnjsub>/if<cnjsub>$ ^àere<vbhaver><pri><p3><sg>/have<vbhaver><pri><p3><sg>$ ^a<pr>/at<pr>/on<pr>/to<pr>$ ^pròere<vblex><inf>/rain<vblex><inf>$ ^cras<adv>/tomorrow<adv>$^.<sent>/.<sent>$
|| Not'#know if #have at rain tomorrow

|-
|8) Una de sas berbekes est maláida. || One of the sheep is sick. || ^Unu<num><f><sp>/One<num><f><sp>$ ^de<pr>/to<pr>/of<pr>$ ^su<det><def><f><pl>/the<det><def><f><pl>$ ^berbeke<n><f><pl>/sheep<n><pl>$ ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$ ^malàidu<adj><f><sg>/sick<adj><f><sg>$^.<sent>/.<sent>$
|| #One to #the sheep #be #sick

|-
|9) Appo pèrditu duos de sos libros meos. || I have lost two of my books. || ^Àere<vbhaver><pri><p1><sg>/Have<vbhaver><pri><p1><sg>$ ^pèrdere<vblex><pp><m><sg>/lose<vblex><pp><m><sg>$ ^duos<num><m><sp>/two<num><m><sp>$ ^de<pr>/to<pr>/of<pr>$ ^su<det><def><m><pl>/the<det><def><m><pl>$ ^libru<n><m><pl>/book<n><pl>$ ^meu<prn><pos><m><pl>/my<prn><pos><m><pl>$^.<sent>/.<sent>$

|| #Have #lose #two to #the books #my

|-
|10) M'an natu ki su trenu devíat arrivare a sas nove. || They told me that the train was supposed to arrive at nine. || ^Mi<prn><pro><p1><mf><sg>/I<prn><pro><p1><mf><sg>$ ^àere<vbhaver><pri><p3><pl>/have<vbhaver><pri><p3><pl>$ ^nàrrere<vblex><pp><m><sg>/tell<vblex><pp><m><sg>$ ^chi<cnjsub>/that<cnjsub>$ ^su<det><def><m><sg>/the<det><def><m><sg>$ ^trenu<n><m><sg>/train<n><sg>$ ^dèvere<vblex><pii><p3><sg>/shall<vbmod><pii><p3><sg>$ ^arrivare<vblex><inf>/arrive<vblex><inf>$ ^a<pr>/at<pr>/on<pr>/to<pr>$ ^su<det><def><f><pl>/the<det><def><f><pl>$ ^nove<num><mf><sp>/nine<num><mf><sp>$^.<sent>/.<sent>$
|| #I #have #tell that #the train #shall arrive at #the #nine
|
|}

==expanding lexicon==

{| cellpadding=5
|medas || many || <adj>
|-https://wikis.swarthmore.edu/ling073/index.php?title=Sardinian_and_English&action=edit
|piseddas || girls || <n><pl>
|-
|sun || they are || <v>
|-
|bennidas || to come (home) || <v><pp><fpl>
|-
|balladu || to dance || <v><pp>
|-
|cantaiat || to sing || <v><sg3>
|-
|sos/sa || the || <det>
|-
|piattos || plates || <n><pl>
|-
|mesa || table || <n><sg>
|-
|bi/b' || N/A || <cl>
|-
|problemas || problems || <n><pl>
|-
|unu || one/a || <adj>/<det>
|-
|ube || where || <adv>
|-
|mortu || dead || <v><pp>
|-
|sordatos || soldiers || <n><pl>
|-
|tenimus || we have || <v><pl1>
|-
|frores || flowers || <n><pl>
|-
|keret || to be necessary || <v><sg3>
|-
|mancat || to be missing || <v><sg3>
|-
|ovos || eggs || <n><pl>
|-
|danca || meadow || <n>
|-
|ortu || orchard || <n>
|-
|frade || brother || <n>
|-
|fizza || daughter || <n>
|-
|re || king || <n>
|-
|ora || hour || <n>
|-
|subra || above/on || <prep>
|-
|a || to/at || <prep>
|-
|cumintzos || origins || <n><pl>
|-
|e || and || <conj>
|-
|andamentu || evolution || <n>
|-
|istòricu || historical || <adj>
|-
|de || of/to || <prep>
|-
|sa || the || <det>
|-
|poesia || poetry || <n>
|-
|a bolu || improvised || <adj> (a bolu = improvised, on the fly)
|-
|in || in || <prep>
|-
|sardu || Sardinian || <n>
|-
|logudoresu || Logudorese || <adj>
|-
|non || not || <adv>
|-
|ischit || known || <v><pp>
|-
|meda || much || <adv>
|-
|custu || this || <det><prox>
|-
|artìculu || article || <n>
|-
|chircat || tries || <v><sg3>
|-
|bogare || to bring out || <v>
|-
|pizu || surface || <n> (bogare a pizu = to shed light on, to bring to the surface; see complicated translations of bogare: [http://vocabolariocasu.isresardegna.it/index.php?key=b&int=0&lemmi=cerca&codice=b1264000 here])
|-
|ammentos || memories || <n><pl>
|-
|ammentu || memory || <n>
|-
|ammentare || to remember || <v>
|-
|documentados || documented || <adj>
|-
|si || [null] || <> -- reflexive
|-
|primas || first || <adj>
|-
|disputas || competitions || <n><pl>
|-
|primas || first || <adj>
|-
|tra || between || <prep>
|-
|poetes || poets || <n><pl>
|-
|cale || which || <prn><rel>
|-
|esserent || were || <v> past imperfect 3rd person plural
|-
|règulas || rules, modalities || <n><pl>
|-
|su || the || <det>
|-
|cunfruntu || confrontation || <n>
|-
|sende || being || <v><ger>
|-
|una || a/one || <art>/<adj>
|-
|chirca || research || <n>
|-
|andera || ongoing/progressive || <adj>
|-
|testu || text || <n>
|-
|diat || [null] || <subj><sg3>
|-
|poder || to be able to || <v><inf>
|-
|aer || to have || <v><inf> (also hàere or àere)
|-
|mudonzos || modifications || <n><pl>
|-
|mudonzos || modifications || <n><pl>
|-
|novas || new || <adj><pl>
|-
|noas || data || <n><pl>
|-
|Pro || to || <prep> <-- keep this in mind for lexical selection (to)
|-
|bider || to read || <v><inf>
|-
|artìculu || article || <n>
|-
|sighire || click on || <v><inf>
|-
|intrare || enter || <v><inf>
|-
|desizadu || desired || <adj>
|-
|trenu || train || <n>
|-
|sinke || [null] || <foc>
|-
|fit || was || <v><imp><sg3>
|-
|andande || leaving || <v><ger>
|-
|at || it will || <>
|-
|sas || the || <det>
|-
|deke || ten || <n>
|-
|devet || should || <adv>
|-
|deke || ten || <adj>
|-
|appo || I have || <v><sg1>
|-
|natu || told || <v><pp>
|-
|próere || to rain || <v><inf>
|-
|arrivare || to arrive || <v><inf>
|-
|isco || I know || <v><sg1>
|-
|si || if || <conj>
|-
|ki || that || <conj>
|-
|cras || tomorrow || <adv>
|-
|meos || my || <pos>
|-
|andatos || gone || <adj><pl>
|
|}

===glosses===

Cando so arrivatu a s'istazione, su trenu sink'andaiat

'when I arrived at the station, the train was leaving'

Su trenu sinke fit andande

'The train was leaving"

Su trenu at a arrivare a sas deke

'The train will arrive at ten o'clock'

Su trenu devet arrivare a sas deke

'The train is supposed to arrive at ten o'clock'

T'appo natu ki su trenu diat arrivare a sas deke

'I told you that the train would arrive at ten o'clock'

M'an natu ki su trenu devíat arrivare a sas nove

'They told me that the train was supposed to arrive at nine'

At a próere cras

'It will rain tomorrow'

Devet próere cras

'it is supposed to rain tomorrow'

At a próere cras? Si emmo abbarramus in domo, ma su nono andamus a mare

'Will it rain tomorrow? If so we shall stay at homr, buy if not we will go to the sea'

No'isco si at a próere cras

'I do to know whether it will rain tomorrow'

Una de sas berbekes est maláida

'one of the sheep is sick'

Appo pèrditu duos de sos libros meos

'I have lost two of my books'

Metas de custas pitzinnas sun galanas

'Many of these girls are pretty'

Una pitzinna meta bella

'a very beautiful girl'

Cussas duas bravas pitzinnas

'those two good girls'

unu better cane bellu

'a huge beautiful dog'

un'átteru bette cane

'another huge dog'

Sun andatos a Frantza

'they went to France'

Est ghiratu dae Corsica

'He returned from Corsica'

Connnosco bene sa Frantza

"i know France well'

Custu libru est iscrittu in tedescu

'This book is written in German'

Cussus paráula venit dae su catalanu

'This word comes from Catalan'

Su sardu est una limba antica

'Sardinian is an ancient language'

Appo mandicatu casu

'I ate cheese'

Laura est toddende frores

'Laura is picking flowers'

De frores non nd'appo tódditu

'I did not pick any flowers'

No'amus comporatu pane

'We did not buy bread'

Mandico sa pasta kin casu

'I ate pasta with cheese'

Tres sórrikes an mandicatu tottu su casu

'Three mice ate all the cheese'

semus ponnende vinu in ampullas

'We are putting wine in bottles'

lettu meu esr

'It is my bed'

No'appo lessu libru perunu

'i did not read any book'

Sos k'an furatu si dinari at a èssere punitos

'The people who stole the money will be punished'

Appo invitat sos de Juanne

'I invited Jon's family'

Cussa pinna est sa mea

'That pen is mine'

Cudda mákkina est sa de Juanne

'That car is John's'

Custa ricca at datu mili francos a su vetzu

'This rich woman gave a thousand lira to the old man'

Su guvernu devíat dare ua pensione a dondzi vetzu

'The government should give a pension to every old person'

==External Resources==

*Github repository for [https://github.com/apertium/apertium-srd Sardinian transducer] (and our [https://github.swarthmore.edu/Ling073-sp23/ling073-srd clone])
*Github repository for [https://github.com/apertium/apertium-eng English transducer]
*[https://www.limbasardasudsardigna.it/sar/images/Documenti/Didatica_e_Ainas/Ditzion%C3%A0riu%20Universale%20Rubattu.pdf Dictionary pdf]
*[http://ditzionariu.sardegnacultura.it/it/ Online official dictionary]
*[https://it.glosbe.com/sc/it Web-based machine translator]
*[http://vocabolariocasu.isresardegna.it/index.php?key=a&int=0&lemmi=cerca Sardinian-Italian web-based dictionary]
*[http://www.sardegnadigitallibrary.it/mmt/fullsize/2009050512495700047.pdf 1931 pdf with select translations]
*[https://onlinelibrary.wiley.com/doi/epdf/10.1111/j.0079-1636.2004.00130.x Definiteness effects: evidence from Sardinian]
*[https://www.icongrouponline.com/en/Detail/dictionary/049783698X/Webster%27s+Sardinian+-+English+Thesaurus+Dictionary: Webster's Sardinian English Thesaurus Dictionary]
*[https://www.academia.edu/15320922/Dizionario_della_lingua_Sarda_Vol_2 Italian-Sardinian Dictionary]
*[https://archive.org/details/vocabolariosardo00spanuoft/page/n361/mode/2up Old but extensive Sardo-Italian and vice versa dictionary]
*[https://limbasardasudsardigna.it/sar/images/Documenti/Didatica_e_Ainas/Vocabolariu_Sardu_Italianu_Spano.pdf nice Sardo-Italiano dictionary pdf]
*[http://www.fontesarda.it/sr/sr0045.htm Conjugations of "to have" in Sardinian]
*[https://sinnainotizie.com/2015/03/07/lezioni-di-grammatica-sardo-campidanese-undicesima-lezione-su-verbu-ai-aere/ Whole Sardinian grammar page about conjugations of to have all written in Sardinian language!]
*Sardinian grammar:[https://www.limbasardasudsardigna.it/sar/images/Documenti/Didatica_e_Ainas/grammatiga_sardo%20campidanese%20A.LEPORI.pdf pdf]
[[Category:Sp23_TranslationPairs]],[[Category:Sardinian]],[[Category:English]]

Sardinian and English

2023-05-04T16:33:08Z

Rorlija1: /* Final evaluation */

=Resources for Machine Translation from Sardinian to English=

==Developed Resources==
*[https://github.swarthmore.edu/Ling073-sp23/ling073-srd-eng-corpus Parallel corpus git repo].
*:Lines 1-8 from [http://maxia-mail.doomby.com/ this website].
*[https://github.swarthmore.edu/Ling073-sp23/ling073-srd-eng Git repo for language pair]
*[https://github.swarthmore.edu/Ling073-sp23/ling073-srd Git repo for Sardinian]
*[https://github.com/apertium/apertium-eng Forked git repo for English]
*[https://wikis.swarthmore.edu/ling073/Sardinian_and_English/Lexical_selection#srd_.E2.86.92_eng Lexical selection wiki]
*[https://wikis.swarthmore.edu/ling073/Sardinian_and_English/Contrastive_Grammar#Differences_in_parse_and_corresponding_examples Contrastive grammar wiki]
*[https://wikis.swarthmore.edu/ling073/Sardinian_and_English/Structural_transfer Structural transfer wiki]

==srd → eng evaluation==
*coverage of monolingual Sardinian transducer on srd.sentences.txt:
Number of tokenised words in the corpus: 262
Coverage: 94.66%
*coverage of bilingual transducer on srd.sentences
Number of tokenised words in the corpus: 266
Coverage: 85.71%

==Additions for polished RBMT system==
*Over 100 new stems to bilingual dictionary
*:(now we have 172 total entries in the .dix file)
*4 sets of lexical selection rules
*:(now we have rules that solve 5 problems in total)
*3 items from contrastive grammar implemented in transfer rules
*:(now we have rules that implement 4 total items)

==Final evaluation==
#* For your monolingual transducer:
#** Updated precision and recall against the (updated) <code>eval.test</code> and <code>eval.gold</code> files (see [[Midterm overview#Evaluating your transducer]]),
#** Coverage over the <code>large</code> corpus,
#** The number of words in the <code>large</code> corpus,
#** The number of stems in the transducer.
#* For MT in the direction we developed (<code>srd-eng</code>):
#** WER and PER over <code>longer</code> corpus.
#** The proportion of stems translated correctly in the <code>longer</code> corpus.
#** Trimmed coverage over <code>longer</code> and <code>large</code> corpora.
#** The number of tokens in <code>longer</code> and <code>large</code> corpora.

==10 sentences glosses and outputs==
*Note: '''These are outputs at end of lexical transfer before lexical selection and other weeks' improvements were implemented'''
{| cellpadding=5
|Sardinian sentence || intended English translation || output of srd-eng-biltrans (lexical transfer) mode || output of srd-eng (full translation) mode
|-
|1) Su sardu est una limba antica. || Sardinian is an ancient language. || ^Su<det><def><m><sg>/The<det><def><m><sg>$ ^sardu<n><m><sg>/Sardinian<n><sg>$ ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$ ^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$^.<sent>/.<sent>$^.<sent>/.<sent>$
|| #The Sardinian #be #a language #ancient
|-
|2) Pro bider s'artìculu sighire custu culligamentu. || To read the article click on this link. || ^Pro<pr>/For<pr>/To<pr>$ ^bider<vblex><inf>/read<vblex><inf>$ ^su<det><def><mf><sg>/the<det><def><mf><sg>$ ^artìculu<n><m><sg>/article<n><sg>$ ^sighire<vblex><inf>/click<vblex><inf>$ ^custu<det><dem><m><sg>/this<det><m><sg>$ ^culligamentu<n><m><sg>/link<n><sg>$^.<sent>/.<sent>$^.<sent>/.<sent>$<m><sg>$ ^culligamentu<n><m><sg>/link<n><sg>$^.<sent>/.<sent>$^.<sent>/.<sent>$
|| For read #the article click #this link.
|-
|3) Su trenu sinke fit andande. || The train was leaving. || ^Su<det><def><m><sg>/The<det><def><m><sg>$ ^trenu<n><m><sg>/train<n><sg>$ ^sinke<cnjadv>/$ ^èssere<vbser><pii><p3><sg>/be<vbser><pii><p3><sg>$ ^andare<vblex><ger>/leave<vblex><ger>/go<vblex><ger>$^.<sent>/.<sent>$^.<sent>/.<sent>$

|| #The train #be leaving.
|-
|4) Su trenu at a arrivare a sas deke. || The train will arrive at ten. || ^Su<det><def><m><sg>/The<det><def><m><sg>$ ^trenu<n><m><sg>/train<n><sg>$ ^àere<vbhaver><pri><p3><sg>/have<vbhaver><pri><p3><sg>$ ^a<pr>/at<pr>/on<pr>/to<pr>$ ^arrivare<vblex><inf>/arrive<vblex><inf>$ ^a<pr>/at<pr>/on<pr>/to<pr>$ ^su<det><def><f><pl>/the<det><def><f><pl>$ ^deke<num><mf><sp>/ten<num><mf><sp>$^.<sent>/.<sent>$^.<sent>/.<sent>$
|| #The train #have at arrive at #the #ten.
|-
|5) Su trenu devet arrivare a sas deke. || The train should arrive at ten. || ^Su<det><def><m><sg>/The<det><def><m><sg>$ ^trenu<n><m><sg>/train<n><sg>$ ^dèvere<vblex><pri><p3><sg>/shall<vbmod><pri><p3><sg>$ ^arrivare<vblex><inf>/arrive<vblex><inf>$ ^a<pr>/at<pr>/on<pr>/to<pr>$ ^su<det><def><f><pl>/the<det><def><f><pl>$ ^deke<num><mf><sp>/ten<num><mf><sp>$^.<sent>/.<sent>$^.<sent>/.<sent>$
|| #The train #shall arrive at #the #ten.
|-
|6) T'appo natu ki su trenu devíat arrivare a sas deke. || I told you that the train would arrive at ten. || ^Ti<prn><pro><p2><mf><sg>/You<prn><pro><p2><mf><sg>$ ^àere<vbhaver><pri><p1><sg>/have<vbhaver><pri><p1><sg>$ ^nàrrere<vblex><pp><m><sg>/tell<vblex><pp><m><sg>$ ^chi<cnjsub>/that<cnjsub>$ ^su<det><def><m><sg>/the<det><def><m><sg>$ ^trenu<n><m><sg>/train<n><sg>$ ^dèvere<vblex><pii><p3><sg>/shall<vbmod><pii><p3><sg>$ ^arrivare<vblex><inf>/arrive<vblex><inf>$ ^a<pr>/at<pr>/on<pr>/to<pr>$ ^su<det><def><f><pl>/the<det><def><f><pl>$ ^deke<num><mf><sp>/ten<num><mf><sp>$^.<sent>/.<sent>$^.<sent>/.<sent>$
|| #You #have #tell that #the train #shall arrive at #the #ten.
|-
|7) No'isco si at a pròere cras. || I do not know if it will rain tomorrow. || ^No<adv>/Not<adv>$'^iscoare<vblex><pri><p1><sg>/know<vblex><pri><p1><sg>$ ^si<cnjsub>/if<cnjsub>$ ^àere<vbhaver><pri><p3><sg>/have<vbhaver><pri><p3><sg>$ ^a<pr>/at<pr>/on<pr>/to<pr>$ ^pròere<vblex><inf>/rain<vblex><inf>$ ^cras<adv>/tomorrow<adv>$^.<sent>/.<sent>$
|| Not'#know if #have at rain tomorrow

|-
|8) Una de sas berbekes est maláida. || One of the sheep is sick. || ^Unu<num><f><sp>/One<num><f><sp>$ ^de<pr>/to<pr>/of<pr>$ ^su<det><def><f><pl>/the<det><def><f><pl>$ ^berbeke<n><f><pl>/sheep<n><pl>$ ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$ ^malàidu<adj><f><sg>/sick<adj><f><sg>$^.<sent>/.<sent>$
|| #One to #the sheep #be #sick

|-
|9) Appo pèrditu duos de sos libros meos. || I have lost two of my books. || ^Àere<vbhaver><pri><p1><sg>/Have<vbhaver><pri><p1><sg>$ ^pèrdere<vblex><pp><m><sg>/lose<vblex><pp><m><sg>$ ^duos<num><m><sp>/two<num><m><sp>$ ^de<pr>/to<pr>/of<pr>$ ^su<det><def><m><pl>/the<det><def><m><pl>$ ^libru<n><m><pl>/book<n><pl>$ ^meu<prn><pos><m><pl>/my<prn><pos><m><pl>$^.<sent>/.<sent>$

|| #Have #lose #two to #the books #my

|-
|10) M'an natu ki su trenu devíat arrivare a sas nove. || They told me that the train was supposed to arrive at nine. || ^Mi<prn><pro><p1><mf><sg>/I<prn><pro><p1><mf><sg>$ ^àere<vbhaver><pri><p3><pl>/have<vbhaver><pri><p3><pl>$ ^nàrrere<vblex><pp><m><sg>/tell<vblex><pp><m><sg>$ ^chi<cnjsub>/that<cnjsub>$ ^su<det><def><m><sg>/the<det><def><m><sg>$ ^trenu<n><m><sg>/train<n><sg>$ ^dèvere<vblex><pii><p3><sg>/shall<vbmod><pii><p3><sg>$ ^arrivare<vblex><inf>/arrive<vblex><inf>$ ^a<pr>/at<pr>/on<pr>/to<pr>$ ^su<det><def><f><pl>/the<det><def><f><pl>$ ^nove<num><mf><sp>/nine<num><mf><sp>$^.<sent>/.<sent>$
|| #I #have #tell that #the train #shall arrive at #the #nine
|
|}

==expanding lexicon==

{| cellpadding=5
|medas || many || <adj>
|-https://wikis.swarthmore.edu/ling073/index.php?title=Sardinian_and_English&action=edit
|piseddas || girls || <n><pl>
|-
|sun || they are || <v>
|-
|bennidas || to come (home) || <v><pp><fpl>
|-
|balladu || to dance || <v><pp>
|-
|cantaiat || to sing || <v><sg3>
|-
|sos/sa || the || <det>
|-
|piattos || plates || <n><pl>
|-
|mesa || table || <n><sg>
|-
|bi/b' || N/A || <cl>
|-
|problemas || problems || <n><pl>
|-
|unu || one/a || <adj>/<det>
|-
|ube || where || <adv>
|-
|mortu || dead || <v><pp>
|-
|sordatos || soldiers || <n><pl>
|-
|tenimus || we have || <v><pl1>
|-
|frores || flowers || <n><pl>
|-
|keret || to be necessary || <v><sg3>
|-
|mancat || to be missing || <v><sg3>
|-
|ovos || eggs || <n><pl>
|-
|danca || meadow || <n>
|-
|ortu || orchard || <n>
|-
|frade || brother || <n>
|-
|fizza || daughter || <n>
|-
|re || king || <n>
|-
|ora || hour || <n>
|-
|subra || above/on || <prep>
|-
|a || to/at || <prep>
|-
|cumintzos || origins || <n><pl>
|-
|e || and || <conj>
|-
|andamentu || evolution || <n>
|-
|istòricu || historical || <adj>
|-
|de || of/to || <prep>
|-
|sa || the || <det>
|-
|poesia || poetry || <n>
|-
|a bolu || improvised || <adj> (a bolu = improvised, on the fly)
|-
|in || in || <prep>
|-
|sardu || Sardinian || <n>
|-
|logudoresu || Logudorese || <adj>
|-
|non || not || <adv>
|-
|ischit || known || <v><pp>
|-
|meda || much || <adv>
|-
|custu || this || <det><prox>
|-
|artìculu || article || <n>
|-
|chircat || tries || <v><sg3>
|-
|bogare || to bring out || <v>
|-
|pizu || surface || <n> (bogare a pizu = to shed light on, to bring to the surface; see complicated translations of bogare: [http://vocabolariocasu.isresardegna.it/index.php?key=b&int=0&lemmi=cerca&codice=b1264000 here])
|-
|ammentos || memories || <n><pl>
|-
|ammentu || memory || <n>
|-
|ammentare || to remember || <v>
|-
|documentados || documented || <adj>
|-
|si || [null] || <> -- reflexive
|-
|primas || first || <adj>
|-
|disputas || competitions || <n><pl>
|-
|primas || first || <adj>
|-
|tra || between || <prep>
|-
|poetes || poets || <n><pl>
|-
|cale || which || <prn><rel>
|-
|esserent || were || <v> past imperfect 3rd person plural
|-
|règulas || rules, modalities || <n><pl>
|-
|su || the || <det>
|-
|cunfruntu || confrontation || <n>
|-
|sende || being || <v><ger>
|-
|una || a/one || <art>/<adj>
|-
|chirca || research || <n>
|-
|andera || ongoing/progressive || <adj>
|-
|testu || text || <n>
|-
|diat || [null] || <subj><sg3>
|-
|poder || to be able to || <v><inf>
|-
|aer || to have || <v><inf> (also hàere or àere)
|-
|mudonzos || modifications || <n><pl>
|-
|mudonzos || modifications || <n><pl>
|-
|novas || new || <adj><pl>
|-
|noas || data || <n><pl>
|-
|Pro || to || <prep> <-- keep this in mind for lexical selection (to)
|-
|bider || to read || <v><inf>
|-
|artìculu || article || <n>
|-
|sighire || click on || <v><inf>
|-
|intrare || enter || <v><inf>
|-
|desizadu || desired || <adj>
|-
|trenu || train || <n>
|-
|sinke || [null] || <foc>
|-
|fit || was || <v><imp><sg3>
|-
|andande || leaving || <v><ger>
|-
|at || it will || <>
|-
|sas || the || <det>
|-
|deke || ten || <n>
|-
|devet || should || <adv>
|-
|deke || ten || <adj>
|-
|appo || I have || <v><sg1>
|-
|natu || told || <v><pp>
|-
|próere || to rain || <v><inf>
|-
|arrivare || to arrive || <v><inf>
|-
|isco || I know || <v><sg1>
|-
|si || if || <conj>
|-
|ki || that || <conj>
|-
|cras || tomorrow || <adv>
|-
|meos || my || <pos>
|-
|andatos || gone || <adj><pl>
|
|}

===glosses===

Cando so arrivatu a s'istazione, su trenu sink'andaiat

'when I arrived at the station, the train was leaving'

Su trenu sinke fit andande

'The train was leaving"

Su trenu at a arrivare a sas deke

'The train will arrive at ten o'clock'

Su trenu devet arrivare a sas deke

'The train is supposed to arrive at ten o'clock'

T'appo natu ki su trenu diat arrivare a sas deke

'I told you that the train would arrive at ten o'clock'

M'an natu ki su trenu devíat arrivare a sas nove

'They told me that the train was supposed to arrive at nine'

At a próere cras

'It will rain tomorrow'

Devet próere cras

'it is supposed to rain tomorrow'

At a próere cras? Si emmo abbarramus in domo, ma su nono andamus a mare

'Will it rain tomorrow? If so we shall stay at homr, buy if not we will go to the sea'

No'isco si at a próere cras

'I do to know whether it will rain tomorrow'

Una de sas berbekes est maláida

'one of the sheep is sick'

Appo pèrditu duos de sos libros meos

'I have lost two of my books'

Metas de custas pitzinnas sun galanas

'Many of these girls are pretty'

Una pitzinna meta bella

'a very beautiful girl'

Cussas duas bravas pitzinnas

'those two good girls'

unu better cane bellu

'a huge beautiful dog'

un'átteru bette cane

'another huge dog'

Sun andatos a Frantza

'they went to France'

Est ghiratu dae Corsica

'He returned from Corsica'

Connnosco bene sa Frantza

"i know France well'

Custu libru est iscrittu in tedescu

'This book is written in German'

Cussus paráula venit dae su catalanu

'This word comes from Catalan'

Su sardu est una limba antica

'Sardinian is an ancient language'

Appo mandicatu casu

'I ate cheese'

Laura est toddende frores

'Laura is picking flowers'

De frores non nd'appo tódditu

'I did not pick any flowers'

No'amus comporatu pane

'We did not buy bread'

Mandico sa pasta kin casu

'I ate pasta with cheese'

Tres sórrikes an mandicatu tottu su casu

'Three mice ate all the cheese'

semus ponnende vinu in ampullas

'We are putting wine in bottles'

lettu meu esr

'It is my bed'

No'appo lessu libru perunu

'i did not read any book'

Sos k'an furatu si dinari at a èssere punitos

'The people who stole the money will be punished'

Appo invitat sos de Juanne

'I invited Jon's family'

Cussa pinna est sa mea

'That pen is mine'

Cudda mákkina est sa de Juanne

'That car is John's'

Custa ricca at datu mili francos a su vetzu

'This rich woman gave a thousand lira to the old man'

Su guvernu devíat dare ua pensione a dondzi vetzu

'The government should give a pension to every old person'

==External Resources==

*Github repository for [https://github.com/apertium/apertium-srd Sardinian transducer] (and our [https://github.swarthmore.edu/Ling073-sp23/ling073-srd clone])
*Github repository for [https://github.com/apertium/apertium-eng English transducer]
*[https://www.limbasardasudsardigna.it/sar/images/Documenti/Didatica_e_Ainas/Ditzion%C3%A0riu%20Universale%20Rubattu.pdf Dictionary pdf]
*[http://ditzionariu.sardegnacultura.it/it/ Online official dictionary]
*[https://it.glosbe.com/sc/it Web-based machine translator]
*[http://vocabolariocasu.isresardegna.it/index.php?key=a&int=0&lemmi=cerca Sardinian-Italian web-based dictionary]
*[http://www.sardegnadigitallibrary.it/mmt/fullsize/2009050512495700047.pdf 1931 pdf with select translations]
*[https://onlinelibrary.wiley.com/doi/epdf/10.1111/j.0079-1636.2004.00130.x Definiteness effects: evidence from Sardinian]
*[https://www.icongrouponline.com/en/Detail/dictionary/049783698X/Webster%27s+Sardinian+-+English+Thesaurus+Dictionary: Webster's Sardinian English Thesaurus Dictionary]
*[https://www.academia.edu/15320922/Dizionario_della_lingua_Sarda_Vol_2 Italian-Sardinian Dictionary]
*[https://archive.org/details/vocabolariosardo00spanuoft/page/n361/mode/2up Old but extensive Sardo-Italian and vice versa dictionary]
*[https://limbasardasudsardigna.it/sar/images/Documenti/Didatica_e_Ainas/Vocabolariu_Sardu_Italianu_Spano.pdf nice Sardo-Italiano dictionary pdf]
*[http://www.fontesarda.it/sr/sr0045.htm Conjugations of "to have" in Sardinian]
*[https://sinnainotizie.com/2015/03/07/lezioni-di-grammatica-sardo-campidanese-undicesima-lezione-su-verbu-ai-aere/ Whole Sardinian grammar page about conjugations of to have all written in Sardinian language!]
*Sardinian grammar:[https://www.limbasardasudsardigna.it/sar/images/Documenti/Didatica_e_Ainas/grammatiga_sardo%20campidanese%20A.LEPORI.pdf pdf]
[[Category:Sp23_TranslationPairs]],[[Category:Sardinian]],[[Category:English]]

Sardinian and English

2023-05-04T16:19:59Z

Rorlija1: /* Resources for Machine Translation from Sardinian to English */

=Resources for Machine Translation from Sardinian to English=

==Developed Resources==
*[https://github.swarthmore.edu/Ling073-sp23/ling073-srd-eng-corpus Parallel corpus git repo].
*:Lines 1-8 from [http://maxia-mail.doomby.com/ this website].
*[https://github.swarthmore.edu/Ling073-sp23/ling073-srd-eng Git repo for language pair]
*[https://github.swarthmore.edu/Ling073-sp23/ling073-srd Git repo for Sardinian]
*[https://github.com/apertium/apertium-eng Forked git repo for English]
*[https://wikis.swarthmore.edu/ling073/Sardinian_and_English/Lexical_selection#srd_.E2.86.92_eng Lexical selection wiki]
*[https://wikis.swarthmore.edu/ling073/Sardinian_and_English/Contrastive_Grammar#Differences_in_parse_and_corresponding_examples Contrastive grammar wiki]
*[https://wikis.swarthmore.edu/ling073/Sardinian_and_English/Structural_transfer Structural transfer wiki]

==srd → eng evaluation==
*coverage of monolingual Sardinian transducer on srd.sentences.txt:
Number of tokenised words in the corpus: 262
Coverage: 94.66%
*coverage of bilingual transducer on srd.sentences
Number of tokenised words in the corpus: 266
Coverage: 85.71%

==Additions for polished RBMT system==
*Over 100 new stems to bilingual dictionary
*:(now we have 172 total entries in the .dix file)
*4 sets of lexical selection rules
*:(now we have rules that solve 5 problems in total)
*3 items from contrastive grammar implemented in transfer rules
*:(now we have rules that implement 4 total items)

==Final evaluation==

==10 sentences glosses and outputs==
*Note: '''These are outputs at end of lexical transfer before lexical selection and other weeks' improvements were implemented'''
{| cellpadding=5
|Sardinian sentence || intended English translation || output of srd-eng-biltrans (lexical transfer) mode || output of srd-eng (full translation) mode
|-
|1) Su sardu est una limba antica. || Sardinian is an ancient language. || ^Su<det><def><m><sg>/The<det><def><m><sg>$ ^sardu<n><m><sg>/Sardinian<n><sg>$ ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$ ^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$^.<sent>/.<sent>$^.<sent>/.<sent>$
|| #The Sardinian #be #a language #ancient
|-
|2) Pro bider s'artìculu sighire custu culligamentu. || To read the article click on this link. || ^Pro<pr>/For<pr>/To<pr>$ ^bider<vblex><inf>/read<vblex><inf>$ ^su<det><def><mf><sg>/the<det><def><mf><sg>$ ^artìculu<n><m><sg>/article<n><sg>$ ^sighire<vblex><inf>/click<vblex><inf>$ ^custu<det><dem><m><sg>/this<det><m><sg>$ ^culligamentu<n><m><sg>/link<n><sg>$^.<sent>/.<sent>$^.<sent>/.<sent>$<m><sg>$ ^culligamentu<n><m><sg>/link<n><sg>$^.<sent>/.<sent>$^.<sent>/.<sent>$
|| For read #the article click #this link.
|-
|3) Su trenu sinke fit andande. || The train was leaving. || ^Su<det><def><m><sg>/The<det><def><m><sg>$ ^trenu<n><m><sg>/train<n><sg>$ ^sinke<cnjadv>/$ ^èssere<vbser><pii><p3><sg>/be<vbser><pii><p3><sg>$ ^andare<vblex><ger>/leave<vblex><ger>/go<vblex><ger>$^.<sent>/.<sent>$^.<sent>/.<sent>$

|| #The train #be leaving.
|-
|4) Su trenu at a arrivare a sas deke. || The train will arrive at ten. || ^Su<det><def><m><sg>/The<det><def><m><sg>$ ^trenu<n><m><sg>/train<n><sg>$ ^àere<vbhaver><pri><p3><sg>/have<vbhaver><pri><p3><sg>$ ^a<pr>/at<pr>/on<pr>/to<pr>$ ^arrivare<vblex><inf>/arrive<vblex><inf>$ ^a<pr>/at<pr>/on<pr>/to<pr>$ ^su<det><def><f><pl>/the<det><def><f><pl>$ ^deke<num><mf><sp>/ten<num><mf><sp>$^.<sent>/.<sent>$^.<sent>/.<sent>$
|| #The train #have at arrive at #the #ten.
|-
|5) Su trenu devet arrivare a sas deke. || The train should arrive at ten. || ^Su<det><def><m><sg>/The<det><def><m><sg>$ ^trenu<n><m><sg>/train<n><sg>$ ^dèvere<vblex><pri><p3><sg>/shall<vbmod><pri><p3><sg>$ ^arrivare<vblex><inf>/arrive<vblex><inf>$ ^a<pr>/at<pr>/on<pr>/to<pr>$ ^su<det><def><f><pl>/the<det><def><f><pl>$ ^deke<num><mf><sp>/ten<num><mf><sp>$^.<sent>/.<sent>$^.<sent>/.<sent>$
|| #The train #shall arrive at #the #ten.
|-
|6) T'appo natu ki su trenu devíat arrivare a sas deke. || I told you that the train would arrive at ten. || ^Ti<prn><pro><p2><mf><sg>/You<prn><pro><p2><mf><sg>$ ^àere<vbhaver><pri><p1><sg>/have<vbhaver><pri><p1><sg>$ ^nàrrere<vblex><pp><m><sg>/tell<vblex><pp><m><sg>$ ^chi<cnjsub>/that<cnjsub>$ ^su<det><def><m><sg>/the<det><def><m><sg>$ ^trenu<n><m><sg>/train<n><sg>$ ^dèvere<vblex><pii><p3><sg>/shall<vbmod><pii><p3><sg>$ ^arrivare<vblex><inf>/arrive<vblex><inf>$ ^a<pr>/at<pr>/on<pr>/to<pr>$ ^su<det><def><f><pl>/the<det><def><f><pl>$ ^deke<num><mf><sp>/ten<num><mf><sp>$^.<sent>/.<sent>$^.<sent>/.<sent>$
|| #You #have #tell that #the train #shall arrive at #the #ten.
|-
|7) No'isco si at a pròere cras. || I do not know if it will rain tomorrow. || ^No<adv>/Not<adv>$'^iscoare<vblex><pri><p1><sg>/know<vblex><pri><p1><sg>$ ^si<cnjsub>/if<cnjsub>$ ^àere<vbhaver><pri><p3><sg>/have<vbhaver><pri><p3><sg>$ ^a<pr>/at<pr>/on<pr>/to<pr>$ ^pròere<vblex><inf>/rain<vblex><inf>$ ^cras<adv>/tomorrow<adv>$^.<sent>/.<sent>$
|| Not'#know if #have at rain tomorrow

|-
|8) Una de sas berbekes est maláida. || One of the sheep is sick. || ^Unu<num><f><sp>/One<num><f><sp>$ ^de<pr>/to<pr>/of<pr>$ ^su<det><def><f><pl>/the<det><def><f><pl>$ ^berbeke<n><f><pl>/sheep<n><pl>$ ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$ ^malàidu<adj><f><sg>/sick<adj><f><sg>$^.<sent>/.<sent>$
|| #One to #the sheep #be #sick

|-
|9) Appo pèrditu duos de sos libros meos. || I have lost two of my books. || ^Àere<vbhaver><pri><p1><sg>/Have<vbhaver><pri><p1><sg>$ ^pèrdere<vblex><pp><m><sg>/lose<vblex><pp><m><sg>$ ^duos<num><m><sp>/two<num><m><sp>$ ^de<pr>/to<pr>/of<pr>$ ^su<det><def><m><pl>/the<det><def><m><pl>$ ^libru<n><m><pl>/book<n><pl>$ ^meu<prn><pos><m><pl>/my<prn><pos><m><pl>$^.<sent>/.<sent>$

|| #Have #lose #two to #the books #my

|-
|10) M'an natu ki su trenu devíat arrivare a sas nove. || They told me that the train was supposed to arrive at nine. || ^Mi<prn><pro><p1><mf><sg>/I<prn><pro><p1><mf><sg>$ ^àere<vbhaver><pri><p3><pl>/have<vbhaver><pri><p3><pl>$ ^nàrrere<vblex><pp><m><sg>/tell<vblex><pp><m><sg>$ ^chi<cnjsub>/that<cnjsub>$ ^su<det><def><m><sg>/the<det><def><m><sg>$ ^trenu<n><m><sg>/train<n><sg>$ ^dèvere<vblex><pii><p3><sg>/shall<vbmod><pii><p3><sg>$ ^arrivare<vblex><inf>/arrive<vblex><inf>$ ^a<pr>/at<pr>/on<pr>/to<pr>$ ^su<det><def><f><pl>/the<det><def><f><pl>$ ^nove<num><mf><sp>/nine<num><mf><sp>$^.<sent>/.<sent>$
|| #I #have #tell that #the train #shall arrive at #the #nine
|
|}

==expanding lexicon==

{| cellpadding=5
|medas || many || <adj>
|-https://wikis.swarthmore.edu/ling073/index.php?title=Sardinian_and_English&action=edit
|piseddas || girls || <n><pl>
|-
|sun || they are || <v>
|-
|bennidas || to come (home) || <v><pp><fpl>
|-
|balladu || to dance || <v><pp>
|-
|cantaiat || to sing || <v><sg3>
|-
|sos/sa || the || <det>
|-
|piattos || plates || <n><pl>
|-
|mesa || table || <n><sg>
|-
|bi/b' || N/A || <cl>
|-
|problemas || problems || <n><pl>
|-
|unu || one/a || <adj>/<det>
|-
|ube || where || <adv>
|-
|mortu || dead || <v><pp>
|-
|sordatos || soldiers || <n><pl>
|-
|tenimus || we have || <v><pl1>
|-
|frores || flowers || <n><pl>
|-
|keret || to be necessary || <v><sg3>
|-
|mancat || to be missing || <v><sg3>
|-
|ovos || eggs || <n><pl>
|-
|danca || meadow || <n>
|-
|ortu || orchard || <n>
|-
|frade || brother || <n>
|-
|fizza || daughter || <n>
|-
|re || king || <n>
|-
|ora || hour || <n>
|-
|subra || above/on || <prep>
|-
|a || to/at || <prep>
|-
|cumintzos || origins || <n><pl>
|-
|e || and || <conj>
|-
|andamentu || evolution || <n>
|-
|istòricu || historical || <adj>
|-
|de || of/to || <prep>
|-
|sa || the || <det>
|-
|poesia || poetry || <n>
|-
|a bolu || improvised || <adj> (a bolu = improvised, on the fly)
|-
|in || in || <prep>
|-
|sardu || Sardinian || <n>
|-
|logudoresu || Logudorese || <adj>
|-
|non || not || <adv>
|-
|ischit || known || <v><pp>
|-
|meda || much || <adv>
|-
|custu || this || <det><prox>
|-
|artìculu || article || <n>
|-
|chircat || tries || <v><sg3>
|-
|bogare || to bring out || <v>
|-
|pizu || surface || <n> (bogare a pizu = to shed light on, to bring to the surface; see complicated translations of bogare: [http://vocabolariocasu.isresardegna.it/index.php?key=b&int=0&lemmi=cerca&codice=b1264000 here])
|-
|ammentos || memories || <n><pl>
|-
|ammentu || memory || <n>
|-
|ammentare || to remember || <v>
|-
|documentados || documented || <adj>
|-
|si || [null] || <> -- reflexive
|-
|primas || first || <adj>
|-
|disputas || competitions || <n><pl>
|-
|primas || first || <adj>
|-
|tra || between || <prep>
|-
|poetes || poets || <n><pl>
|-
|cale || which || <prn><rel>
|-
|esserent || were || <v> past imperfect 3rd person plural
|-
|règulas || rules, modalities || <n><pl>
|-
|su || the || <det>
|-
|cunfruntu || confrontation || <n>
|-
|sende || being || <v><ger>
|-
|una || a/one || <art>/<adj>
|-
|chirca || research || <n>
|-
|andera || ongoing/progressive || <adj>
|-
|testu || text || <n>
|-
|diat || [null] || <subj><sg3>
|-
|poder || to be able to || <v><inf>
|-
|aer || to have || <v><inf> (also hàere or àere)
|-
|mudonzos || modifications || <n><pl>
|-
|mudonzos || modifications || <n><pl>
|-
|novas || new || <adj><pl>
|-
|noas || data || <n><pl>
|-
|Pro || to || <prep> <-- keep this in mind for lexical selection (to)
|-
|bider || to read || <v><inf>
|-
|artìculu || article || <n>
|-
|sighire || click on || <v><inf>
|-
|intrare || enter || <v><inf>
|-
|desizadu || desired || <adj>
|-
|trenu || train || <n>
|-
|sinke || [null] || <foc>
|-
|fit || was || <v><imp><sg3>
|-
|andande || leaving || <v><ger>
|-
|at || it will || <>
|-
|sas || the || <det>
|-
|deke || ten || <n>
|-
|devet || should || <adv>
|-
|deke || ten || <adj>
|-
|appo || I have || <v><sg1>
|-
|natu || told || <v><pp>
|-
|próere || to rain || <v><inf>
|-
|arrivare || to arrive || <v><inf>
|-
|isco || I know || <v><sg1>
|-
|si || if || <conj>
|-
|ki || that || <conj>
|-
|cras || tomorrow || <adv>
|-
|meos || my || <pos>
|-
|andatos || gone || <adj><pl>
|
|}

===glosses===

Cando so arrivatu a s'istazione, su trenu sink'andaiat

'when I arrived at the station, the train was leaving'

Su trenu sinke fit andande

'The train was leaving"

Su trenu at a arrivare a sas deke

'The train will arrive at ten o'clock'

Su trenu devet arrivare a sas deke

'The train is supposed to arrive at ten o'clock'

T'appo natu ki su trenu diat arrivare a sas deke

'I told you that the train would arrive at ten o'clock'

M'an natu ki su trenu devíat arrivare a sas nove

'They told me that the train was supposed to arrive at nine'

At a próere cras

'It will rain tomorrow'

Devet próere cras

'it is supposed to rain tomorrow'

At a próere cras? Si emmo abbarramus in domo, ma su nono andamus a mare

'Will it rain tomorrow? If so we shall stay at homr, buy if not we will go to the sea'

No'isco si at a próere cras

'I do to know whether it will rain tomorrow'

Una de sas berbekes est maláida

'one of the sheep is sick'

Appo pèrditu duos de sos libros meos

'I have lost two of my books'

Metas de custas pitzinnas sun galanas

'Many of these girls are pretty'

Una pitzinna meta bella

'a very beautiful girl'

Cussas duas bravas pitzinnas

'those two good girls'

unu better cane bellu

'a huge beautiful dog'

un'átteru bette cane

'another huge dog'

Sun andatos a Frantza

'they went to France'

Est ghiratu dae Corsica

'He returned from Corsica'

Connnosco bene sa Frantza

"i know France well'

Custu libru est iscrittu in tedescu

'This book is written in German'

Cussus paráula venit dae su catalanu

'This word comes from Catalan'

Su sardu est una limba antica

'Sardinian is an ancient language'

Appo mandicatu casu

'I ate cheese'

Laura est toddende frores

'Laura is picking flowers'

De frores non nd'appo tódditu

'I did not pick any flowers'

No'amus comporatu pane

'We did not buy bread'

Mandico sa pasta kin casu

'I ate pasta with cheese'

Tres sórrikes an mandicatu tottu su casu

'Three mice ate all the cheese'

semus ponnende vinu in ampullas

'We are putting wine in bottles'

lettu meu esr

'It is my bed'

No'appo lessu libru perunu

'i did not read any book'

Sos k'an furatu si dinari at a èssere punitos

'The people who stole the money will be punished'

Appo invitat sos de Juanne

'I invited Jon's family'

Cussa pinna est sa mea

'That pen is mine'

Cudda mákkina est sa de Juanne

'That car is John's'

Custa ricca at datu mili francos a su vetzu

'This rich woman gave a thousand lira to the old man'

Su guvernu devíat dare ua pensione a dondzi vetzu

'The government should give a pension to every old person'

==External Resources==

*Github repository for [https://github.com/apertium/apertium-srd Sardinian transducer] (and our [https://github.swarthmore.edu/Ling073-sp23/ling073-srd clone])
*Github repository for [https://github.com/apertium/apertium-eng English transducer]
*[https://www.limbasardasudsardigna.it/sar/images/Documenti/Didatica_e_Ainas/Ditzion%C3%A0riu%20Universale%20Rubattu.pdf Dictionary pdf]
*[http://ditzionariu.sardegnacultura.it/it/ Online official dictionary]
*[https://it.glosbe.com/sc/it Web-based machine translator]
*[http://vocabolariocasu.isresardegna.it/index.php?key=a&int=0&lemmi=cerca Sardinian-Italian web-based dictionary]
*[http://www.sardegnadigitallibrary.it/mmt/fullsize/2009050512495700047.pdf 1931 pdf with select translations]
*[https://onlinelibrary.wiley.com/doi/epdf/10.1111/j.0079-1636.2004.00130.x Definiteness effects: evidence from Sardinian]
*[https://www.icongrouponline.com/en/Detail/dictionary/049783698X/Webster%27s+Sardinian+-+English+Thesaurus+Dictionary: Webster's Sardinian English Thesaurus Dictionary]
*[https://www.academia.edu/15320922/Dizionario_della_lingua_Sarda_Vol_2 Italian-Sardinian Dictionary]
*[https://archive.org/details/vocabolariosardo00spanuoft/page/n361/mode/2up Old but extensive Sardo-Italian and vice versa dictionary]
*[https://limbasardasudsardigna.it/sar/images/Documenti/Didatica_e_Ainas/Vocabolariu_Sardu_Italianu_Spano.pdf nice Sardo-Italiano dictionary pdf]
*[http://www.fontesarda.it/sr/sr0045.htm Conjugations of "to have" in Sardinian]
*[https://sinnainotizie.com/2015/03/07/lezioni-di-grammatica-sardo-campidanese-undicesima-lezione-su-verbu-ai-aere/ Whole Sardinian grammar page about conjugations of to have all written in Sardinian language!]
*Sardinian grammar:[https://www.limbasardasudsardigna.it/sar/images/Documenti/Didatica_e_Ainas/grammatiga_sardo%20campidanese%20A.LEPORI.pdf pdf]
[[Category:Sp23_TranslationPairs]],[[Category:Sardinian]],[[Category:English]]

Sardinian and English

2023-05-04T16:18:01Z

Rorlija1: /* Notes for improvement */

=Resources for Machine Translation from Sardinian to English=

==Developed Resources==
*[https://github.swarthmore.edu/Ling073-sp23/ling073-srd-eng-corpus Parallel corpus git repo].
*:Lines 1-8 from [http://maxia-mail.doomby.com/ this website].
*[https://github.swarthmore.edu/Ling073-sp23/ling073-srd-eng Git repo for language pair]
*[https://github.swarthmore.edu/Ling073-sp23/ling073-srd Git repo for Sardinian]
*[https://github.com/apertium/apertium-eng Forked git repo for English]
*[https://wikis.swarthmore.edu/ling073/Sardinian_and_English/Lexical_selection#srd_.E2.86.92_eng Lexical selection wiki]
*[https://wikis.swarthmore.edu/ling073/Sardinian_and_English/Contrastive_Grammar#Differences_in_parse_and_corresponding_examples Contrastive grammar wiki]
*[https://wikis.swarthmore.edu/ling073/Sardinian_and_English/Structural_transfer Structural transfer wiki]

==srd → eng evaluation==
*coverage of monolingual Sardinian transducer on srd.sentences.txt:
Number of tokenised words in the corpus: 262
Coverage: 94.66%
*coverage of bilingual transducer on srd.sentences
Number of tokenised words in the corpus: 266
Coverage: 85.71%

==10 sentences glosses and outputs==
*Note: '''These are outputs at end of lexical transfer before lexical selection and other weeks' improvements were implemented'''
{| cellpadding=5
|Sardinian sentence || intended English translation || output of srd-eng-biltrans (lexical transfer) mode || output of srd-eng (full translation) mode
|-
|1) Su sardu est una limba antica. || Sardinian is an ancient language. || ^Su<det><def><m><sg>/The<det><def><m><sg>$ ^sardu<n><m><sg>/Sardinian<n><sg>$ ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$ ^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$^.<sent>/.<sent>$^.<sent>/.<sent>$
|| #The Sardinian #be #a language #ancient
|-
|2) Pro bider s'artìculu sighire custu culligamentu. || To read the article click on this link. || ^Pro<pr>/For<pr>/To<pr>$ ^bider<vblex><inf>/read<vblex><inf>$ ^su<det><def><mf><sg>/the<det><def><mf><sg>$ ^artìculu<n><m><sg>/article<n><sg>$ ^sighire<vblex><inf>/click<vblex><inf>$ ^custu<det><dem><m><sg>/this<det><m><sg>$ ^culligamentu<n><m><sg>/link<n><sg>$^.<sent>/.<sent>$^.<sent>/.<sent>$<m><sg>$ ^culligamentu<n><m><sg>/link<n><sg>$^.<sent>/.<sent>$^.<sent>/.<sent>$
|| For read #the article click #this link.
|-
|3) Su trenu sinke fit andande. || The train was leaving. || ^Su<det><def><m><sg>/The<det><def><m><sg>$ ^trenu<n><m><sg>/train<n><sg>$ ^sinke<cnjadv>/$ ^èssere<vbser><pii><p3><sg>/be<vbser><pii><p3><sg>$ ^andare<vblex><ger>/leave<vblex><ger>/go<vblex><ger>$^.<sent>/.<sent>$^.<sent>/.<sent>$

|| #The train #be leaving.
|-
|4) Su trenu at a arrivare a sas deke. || The train will arrive at ten. || ^Su<det><def><m><sg>/The<det><def><m><sg>$ ^trenu<n><m><sg>/train<n><sg>$ ^àere<vbhaver><pri><p3><sg>/have<vbhaver><pri><p3><sg>$ ^a<pr>/at<pr>/on<pr>/to<pr>$ ^arrivare<vblex><inf>/arrive<vblex><inf>$ ^a<pr>/at<pr>/on<pr>/to<pr>$ ^su<det><def><f><pl>/the<det><def><f><pl>$ ^deke<num><mf><sp>/ten<num><mf><sp>$^.<sent>/.<sent>$^.<sent>/.<sent>$
|| #The train #have at arrive at #the #ten.
|-
|5) Su trenu devet arrivare a sas deke. || The train should arrive at ten. || ^Su<det><def><m><sg>/The<det><def><m><sg>$ ^trenu<n><m><sg>/train<n><sg>$ ^dèvere<vblex><pri><p3><sg>/shall<vbmod><pri><p3><sg>$ ^arrivare<vblex><inf>/arrive<vblex><inf>$ ^a<pr>/at<pr>/on<pr>/to<pr>$ ^su<det><def><f><pl>/the<det><def><f><pl>$ ^deke<num><mf><sp>/ten<num><mf><sp>$^.<sent>/.<sent>$^.<sent>/.<sent>$
|| #The train #shall arrive at #the #ten.
|-
|6) T'appo natu ki su trenu devíat arrivare a sas deke. || I told you that the train would arrive at ten. || ^Ti<prn><pro><p2><mf><sg>/You<prn><pro><p2><mf><sg>$ ^àere<vbhaver><pri><p1><sg>/have<vbhaver><pri><p1><sg>$ ^nàrrere<vblex><pp><m><sg>/tell<vblex><pp><m><sg>$ ^chi<cnjsub>/that<cnjsub>$ ^su<det><def><m><sg>/the<det><def><m><sg>$ ^trenu<n><m><sg>/train<n><sg>$ ^dèvere<vblex><pii><p3><sg>/shall<vbmod><pii><p3><sg>$ ^arrivare<vblex><inf>/arrive<vblex><inf>$ ^a<pr>/at<pr>/on<pr>/to<pr>$ ^su<det><def><f><pl>/the<det><def><f><pl>$ ^deke<num><mf><sp>/ten<num><mf><sp>$^.<sent>/.<sent>$^.<sent>/.<sent>$
|| #You #have #tell that #the train #shall arrive at #the #ten.
|-
|7) No'isco si at a pròere cras. || I do not know if it will rain tomorrow. || ^No<adv>/Not<adv>$'^iscoare<vblex><pri><p1><sg>/know<vblex><pri><p1><sg>$ ^si<cnjsub>/if<cnjsub>$ ^àere<vbhaver><pri><p3><sg>/have<vbhaver><pri><p3><sg>$ ^a<pr>/at<pr>/on<pr>/to<pr>$ ^pròere<vblex><inf>/rain<vblex><inf>$ ^cras<adv>/tomorrow<adv>$^.<sent>/.<sent>$
|| Not'#know if #have at rain tomorrow

|-
|8) Una de sas berbekes est maláida. || One of the sheep is sick. || ^Unu<num><f><sp>/One<num><f><sp>$ ^de<pr>/to<pr>/of<pr>$ ^su<det><def><f><pl>/the<det><def><f><pl>$ ^berbeke<n><f><pl>/sheep<n><pl>$ ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$ ^malàidu<adj><f><sg>/sick<adj><f><sg>$^.<sent>/.<sent>$
|| #One to #the sheep #be #sick

|-
|9) Appo pèrditu duos de sos libros meos. || I have lost two of my books. || ^Àere<vbhaver><pri><p1><sg>/Have<vbhaver><pri><p1><sg>$ ^pèrdere<vblex><pp><m><sg>/lose<vblex><pp><m><sg>$ ^duos<num><m><sp>/two<num><m><sp>$ ^de<pr>/to<pr>/of<pr>$ ^su<det><def><m><pl>/the<det><def><m><pl>$ ^libru<n><m><pl>/book<n><pl>$ ^meu<prn><pos><m><pl>/my<prn><pos><m><pl>$^.<sent>/.<sent>$

|| #Have #lose #two to #the books #my

|-
|10) M'an natu ki su trenu devíat arrivare a sas nove. || They told me that the train was supposed to arrive at nine. || ^Mi<prn><pro><p1><mf><sg>/I<prn><pro><p1><mf><sg>$ ^àere<vbhaver><pri><p3><pl>/have<vbhaver><pri><p3><pl>$ ^nàrrere<vblex><pp><m><sg>/tell<vblex><pp><m><sg>$ ^chi<cnjsub>/that<cnjsub>$ ^su<det><def><m><sg>/the<det><def><m><sg>$ ^trenu<n><m><sg>/train<n><sg>$ ^dèvere<vblex><pii><p3><sg>/shall<vbmod><pii><p3><sg>$ ^arrivare<vblex><inf>/arrive<vblex><inf>$ ^a<pr>/at<pr>/on<pr>/to<pr>$ ^su<det><def><f><pl>/the<det><def><f><pl>$ ^nove<num><mf><sp>/nine<num><mf><sp>$^.<sent>/.<sent>$
|| #I #have #tell that #the train #shall arrive at #the #nine
|
|}

==Additions for polished RBMT system==
*Over 100 new stems to bilingual dictionary
*:(now we have 172 total entries in the .dix file)
*4 sets of lexical selection rules
*:(now we have rules that solve 5 problems in total)
*3 items from contrastive grammar implemented in transfer rules
*:(now we have rules that implement 4 total items)

==expanding lexicon==

{| cellpadding=5
|medas || many || <adj>
|-https://wikis.swarthmore.edu/ling073/index.php?title=Sardinian_and_English&action=edit
|piseddas || girls || <n><pl>
|-
|sun || they are || <v>
|-
|bennidas || to come (home) || <v><pp><fpl>
|-
|balladu || to dance || <v><pp>
|-
|cantaiat || to sing || <v><sg3>
|-
|sos/sa || the || <det>
|-
|piattos || plates || <n><pl>
|-
|mesa || table || <n><sg>
|-
|bi/b' || N/A || <cl>
|-
|problemas || problems || <n><pl>
|-
|unu || one/a || <adj>/<det>
|-
|ube || where || <adv>
|-
|mortu || dead || <v><pp>
|-
|sordatos || soldiers || <n><pl>
|-
|tenimus || we have || <v><pl1>
|-
|frores || flowers || <n><pl>
|-
|keret || to be necessary || <v><sg3>
|-
|mancat || to be missing || <v><sg3>
|-
|ovos || eggs || <n><pl>
|-
|danca || meadow || <n>
|-
|ortu || orchard || <n>
|-
|frade || brother || <n>
|-
|fizza || daughter || <n>
|-
|re || king || <n>
|-
|ora || hour || <n>
|-
|subra || above/on || <prep>
|-
|a || to/at || <prep>
|-
|cumintzos || origins || <n><pl>
|-
|e || and || <conj>
|-
|andamentu || evolution || <n>
|-
|istòricu || historical || <adj>
|-
|de || of/to || <prep>
|-
|sa || the || <det>
|-
|poesia || poetry || <n>
|-
|a bolu || improvised || <adj> (a bolu = improvised, on the fly)
|-
|in || in || <prep>
|-
|sardu || Sardinian || <n>
|-
|logudoresu || Logudorese || <adj>
|-
|non || not || <adv>
|-
|ischit || known || <v><pp>
|-
|meda || much || <adv>
|-
|custu || this || <det><prox>
|-
|artìculu || article || <n>
|-
|chircat || tries || <v><sg3>
|-
|bogare || to bring out || <v>
|-
|pizu || surface || <n> (bogare a pizu = to shed light on, to bring to the surface; see complicated translations of bogare: [http://vocabolariocasu.isresardegna.it/index.php?key=b&int=0&lemmi=cerca&codice=b1264000 here])
|-
|ammentos || memories || <n><pl>
|-
|ammentu || memory || <n>
|-
|ammentare || to remember || <v>
|-
|documentados || documented || <adj>
|-
|si || [null] || <> -- reflexive
|-
|primas || first || <adj>
|-
|disputas || competitions || <n><pl>
|-
|primas || first || <adj>
|-
|tra || between || <prep>
|-
|poetes || poets || <n><pl>
|-
|cale || which || <prn><rel>
|-
|esserent || were || <v> past imperfect 3rd person plural
|-
|règulas || rules, modalities || <n><pl>
|-
|su || the || <det>
|-
|cunfruntu || confrontation || <n>
|-
|sende || being || <v><ger>
|-
|una || a/one || <art>/<adj>
|-
|chirca || research || <n>
|-
|andera || ongoing/progressive || <adj>
|-
|testu || text || <n>
|-
|diat || [null] || <subj><sg3>
|-
|poder || to be able to || <v><inf>
|-
|aer || to have || <v><inf> (also hàere or àere)
|-
|mudonzos || modifications || <n><pl>
|-
|mudonzos || modifications || <n><pl>
|-
|novas || new || <adj><pl>
|-
|noas || data || <n><pl>
|-
|Pro || to || <prep> <-- keep this in mind for lexical selection (to)
|-
|bider || to read || <v><inf>
|-
|artìculu || article || <n>
|-
|sighire || click on || <v><inf>
|-
|intrare || enter || <v><inf>
|-
|desizadu || desired || <adj>
|-
|trenu || train || <n>
|-
|sinke || [null] || <foc>
|-
|fit || was || <v><imp><sg3>
|-
|andande || leaving || <v><ger>
|-
|at || it will || <>
|-
|sas || the || <det>
|-
|deke || ten || <n>
|-
|devet || should || <adv>
|-
|deke || ten || <adj>
|-
|appo || I have || <v><sg1>
|-
|natu || told || <v><pp>
|-
|próere || to rain || <v><inf>
|-
|arrivare || to arrive || <v><inf>
|-
|isco || I know || <v><sg1>
|-
|si || if || <conj>
|-
|ki || that || <conj>
|-
|cras || tomorrow || <adv>
|-
|meos || my || <pos>
|-
|andatos || gone || <adj><pl>
|
|}

===glosses===

Cando so arrivatu a s'istazione, su trenu sink'andaiat

'when I arrived at the station, the train was leaving'

Su trenu sinke fit andande

'The train was leaving"

Su trenu at a arrivare a sas deke

'The train will arrive at ten o'clock'

Su trenu devet arrivare a sas deke

'The train is supposed to arrive at ten o'clock'

T'appo natu ki su trenu diat arrivare a sas deke

'I told you that the train would arrive at ten o'clock'

M'an natu ki su trenu devíat arrivare a sas nove

'They told me that the train was supposed to arrive at nine'

At a próere cras

'It will rain tomorrow'

Devet próere cras

'it is supposed to rain tomorrow'

At a próere cras? Si emmo abbarramus in domo, ma su nono andamus a mare

'Will it rain tomorrow? If so we shall stay at homr, buy if not we will go to the sea'

No'isco si at a próere cras

'I do to know whether it will rain tomorrow'

Una de sas berbekes est maláida

'one of the sheep is sick'

Appo pèrditu duos de sos libros meos

'I have lost two of my books'

Metas de custas pitzinnas sun galanas

'Many of these girls are pretty'

Una pitzinna meta bella

'a very beautiful girl'

Cussas duas bravas pitzinnas

'those two good girls'

unu better cane bellu

'a huge beautiful dog'

un'átteru bette cane

'another huge dog'

Sun andatos a Frantza

'they went to France'

Est ghiratu dae Corsica

'He returned from Corsica'

Connnosco bene sa Frantza

"i know France well'

Custu libru est iscrittu in tedescu

'This book is written in German'

Cussus paráula venit dae su catalanu

'This word comes from Catalan'

Su sardu est una limba antica

'Sardinian is an ancient language'

Appo mandicatu casu

'I ate cheese'

Laura est toddende frores

'Laura is picking flowers'

De frores non nd'appo tódditu

'I did not pick any flowers'

No'amus comporatu pane

'We did not buy bread'

Mandico sa pasta kin casu

'I ate pasta with cheese'

Tres sórrikes an mandicatu tottu su casu

'Three mice ate all the cheese'

semus ponnende vinu in ampullas

'We are putting wine in bottles'

lettu meu esr

'It is my bed'

No'appo lessu libru perunu

'i did not read any book'

Sos k'an furatu si dinari at a èssere punitos

'The people who stole the money will be punished'

Appo invitat sos de Juanne

'I invited Jon's family'

Cussa pinna est sa mea

'That pen is mine'

Cudda mákkina est sa de Juanne

'That car is John's'

Custa ricca at datu mili francos a su vetzu

'This rich woman gave a thousand lira to the old man'

Su guvernu devíat dare ua pensione a dondzi vetzu

'The government should give a pension to every old person'

==External Resources==

*Github repository for [https://github.com/apertium/apertium-srd Sardinian transducer] (and our [https://github.swarthmore.edu/Ling073-sp23/ling073-srd clone])
*Github repository for [https://github.com/apertium/apertium-eng English transducer]
*[https://www.limbasardasudsardigna.it/sar/images/Documenti/Didatica_e_Ainas/Ditzion%C3%A0riu%20Universale%20Rubattu.pdf Dictionary pdf]
*[http://ditzionariu.sardegnacultura.it/it/ Online official dictionary]
*[https://it.glosbe.com/sc/it Web-based machine translator]
*[http://vocabolariocasu.isresardegna.it/index.php?key=a&int=0&lemmi=cerca Sardinian-Italian web-based dictionary]
*[http://www.sardegnadigitallibrary.it/mmt/fullsize/2009050512495700047.pdf 1931 pdf with select translations]
*[https://onlinelibrary.wiley.com/doi/epdf/10.1111/j.0079-1636.2004.00130.x Definiteness effects: evidence from Sardinian]
*[https://www.icongrouponline.com/en/Detail/dictionary/049783698X/Webster%27s+Sardinian+-+English+Thesaurus+Dictionary: Webster's Sardinian English Thesaurus Dictionary]
*[https://www.academia.edu/15320922/Dizionario_della_lingua_Sarda_Vol_2 Italian-Sardinian Dictionary]
*[https://archive.org/details/vocabolariosardo00spanuoft/page/n361/mode/2up Old but extensive Sardo-Italian and vice versa dictionary]
*[https://limbasardasudsardigna.it/sar/images/Documenti/Didatica_e_Ainas/Vocabolariu_Sardu_Italianu_Spano.pdf nice Sardo-Italiano dictionary pdf]
*[http://www.fontesarda.it/sr/sr0045.htm Conjugations of "to have" in Sardinian]
*[https://sinnainotizie.com/2015/03/07/lezioni-di-grammatica-sardo-campidanese-undicesima-lezione-su-verbu-ai-aere/ Whole Sardinian grammar page about conjugations of to have all written in Sardinian language!]
*Sardinian grammar:[https://www.limbasardasudsardigna.it/sar/images/Documenti/Didatica_e_Ainas/grammatiga_sardo%20campidanese%20A.LEPORI.pdf pdf]
[[Category:Sp23_TranslationPairs]],[[Category:Sardinian]],[[Category:English]]

Sardinian and English

2023-05-04T16:17:37Z

Rorlija1: /* Resources for Machine Translation from Sardinian to English */

=Resources for Machine Translation from Sardinian to English=

==Developed Resources==
*[https://github.swarthmore.edu/Ling073-sp23/ling073-srd-eng-corpus Parallel corpus git repo].
*:Lines 1-8 from [http://maxia-mail.doomby.com/ this website].
*[https://github.swarthmore.edu/Ling073-sp23/ling073-srd-eng Git repo for language pair]
*[https://github.swarthmore.edu/Ling073-sp23/ling073-srd Git repo for Sardinian]
*[https://github.com/apertium/apertium-eng Forked git repo for English]
*[https://wikis.swarthmore.edu/ling073/Sardinian_and_English/Lexical_selection#srd_.E2.86.92_eng Lexical selection wiki]
*[https://wikis.swarthmore.edu/ling073/Sardinian_and_English/Contrastive_Grammar#Differences_in_parse_and_corresponding_examples Contrastive grammar wiki]
*[https://wikis.swarthmore.edu/ling073/Sardinian_and_English/Structural_transfer Structural transfer wiki]

==srd → eng evaluation==
*coverage of monolingual Sardinian transducer on srd.sentences.txt:
Number of tokenised words in the corpus: 262
Coverage: 94.66%
*coverage of bilingual transducer on srd.sentences
Number of tokenised words in the corpus: 266
Coverage: 85.71%

==10 sentences glosses and outputs==
*Note: '''These are outputs at end of lexical transfer before lexical selection and other weeks' improvements were implemented'''
{| cellpadding=5
|Sardinian sentence || intended English translation || output of srd-eng-biltrans (lexical transfer) mode || output of srd-eng (full translation) mode
|-
|1) Su sardu est una limba antica. || Sardinian is an ancient language. || ^Su<det><def><m><sg>/The<det><def><m><sg>$ ^sardu<n><m><sg>/Sardinian<n><sg>$ ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$ ^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$^.<sent>/.<sent>$^.<sent>/.<sent>$
|| #The Sardinian #be #a language #ancient
|-
|2) Pro bider s'artìculu sighire custu culligamentu. || To read the article click on this link. || ^Pro<pr>/For<pr>/To<pr>$ ^bider<vblex><inf>/read<vblex><inf>$ ^su<det><def><mf><sg>/the<det><def><mf><sg>$ ^artìculu<n><m><sg>/article<n><sg>$ ^sighire<vblex><inf>/click<vblex><inf>$ ^custu<det><dem><m><sg>/this<det><m><sg>$ ^culligamentu<n><m><sg>/link<n><sg>$^.<sent>/.<sent>$^.<sent>/.<sent>$<m><sg>$ ^culligamentu<n><m><sg>/link<n><sg>$^.<sent>/.<sent>$^.<sent>/.<sent>$
|| For read #the article click #this link.
|-
|3) Su trenu sinke fit andande. || The train was leaving. || ^Su<det><def><m><sg>/The<det><def><m><sg>$ ^trenu<n><m><sg>/train<n><sg>$ ^sinke<cnjadv>/$ ^èssere<vbser><pii><p3><sg>/be<vbser><pii><p3><sg>$ ^andare<vblex><ger>/leave<vblex><ger>/go<vblex><ger>$^.<sent>/.<sent>$^.<sent>/.<sent>$

|| #The train #be leaving.
|-
|4) Su trenu at a arrivare a sas deke. || The train will arrive at ten. || ^Su<det><def><m><sg>/The<det><def><m><sg>$ ^trenu<n><m><sg>/train<n><sg>$ ^àere<vbhaver><pri><p3><sg>/have<vbhaver><pri><p3><sg>$ ^a<pr>/at<pr>/on<pr>/to<pr>$ ^arrivare<vblex><inf>/arrive<vblex><inf>$ ^a<pr>/at<pr>/on<pr>/to<pr>$ ^su<det><def><f><pl>/the<det><def><f><pl>$ ^deke<num><mf><sp>/ten<num><mf><sp>$^.<sent>/.<sent>$^.<sent>/.<sent>$
|| #The train #have at arrive at #the #ten.
|-
|5) Su trenu devet arrivare a sas deke. || The train should arrive at ten. || ^Su<det><def><m><sg>/The<det><def><m><sg>$ ^trenu<n><m><sg>/train<n><sg>$ ^dèvere<vblex><pri><p3><sg>/shall<vbmod><pri><p3><sg>$ ^arrivare<vblex><inf>/arrive<vblex><inf>$ ^a<pr>/at<pr>/on<pr>/to<pr>$ ^su<det><def><f><pl>/the<det><def><f><pl>$ ^deke<num><mf><sp>/ten<num><mf><sp>$^.<sent>/.<sent>$^.<sent>/.<sent>$
|| #The train #shall arrive at #the #ten.
|-
|6) T'appo natu ki su trenu devíat arrivare a sas deke. || I told you that the train would arrive at ten. || ^Ti<prn><pro><p2><mf><sg>/You<prn><pro><p2><mf><sg>$ ^àere<vbhaver><pri><p1><sg>/have<vbhaver><pri><p1><sg>$ ^nàrrere<vblex><pp><m><sg>/tell<vblex><pp><m><sg>$ ^chi<cnjsub>/that<cnjsub>$ ^su<det><def><m><sg>/the<det><def><m><sg>$ ^trenu<n><m><sg>/train<n><sg>$ ^dèvere<vblex><pii><p3><sg>/shall<vbmod><pii><p3><sg>$ ^arrivare<vblex><inf>/arrive<vblex><inf>$ ^a<pr>/at<pr>/on<pr>/to<pr>$ ^su<det><def><f><pl>/the<det><def><f><pl>$ ^deke<num><mf><sp>/ten<num><mf><sp>$^.<sent>/.<sent>$^.<sent>/.<sent>$
|| #You #have #tell that #the train #shall arrive at #the #ten.
|-
|7) No'isco si at a pròere cras. || I do not know if it will rain tomorrow. || ^No<adv>/Not<adv>$'^iscoare<vblex><pri><p1><sg>/know<vblex><pri><p1><sg>$ ^si<cnjsub>/if<cnjsub>$ ^àere<vbhaver><pri><p3><sg>/have<vbhaver><pri><p3><sg>$ ^a<pr>/at<pr>/on<pr>/to<pr>$ ^pròere<vblex><inf>/rain<vblex><inf>$ ^cras<adv>/tomorrow<adv>$^.<sent>/.<sent>$
|| Not'#know if #have at rain tomorrow

|-
|8) Una de sas berbekes est maláida. || One of the sheep is sick. || ^Unu<num><f><sp>/One<num><f><sp>$ ^de<pr>/to<pr>/of<pr>$ ^su<det><def><f><pl>/the<det><def><f><pl>$ ^berbeke<n><f><pl>/sheep<n><pl>$ ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$ ^malàidu<adj><f><sg>/sick<adj><f><sg>$^.<sent>/.<sent>$
|| #One to #the sheep #be #sick

|-
|9) Appo pèrditu duos de sos libros meos. || I have lost two of my books. || ^Àere<vbhaver><pri><p1><sg>/Have<vbhaver><pri><p1><sg>$ ^pèrdere<vblex><pp><m><sg>/lose<vblex><pp><m><sg>$ ^duos<num><m><sp>/two<num><m><sp>$ ^de<pr>/to<pr>/of<pr>$ ^su<det><def><m><pl>/the<det><def><m><pl>$ ^libru<n><m><pl>/book<n><pl>$ ^meu<prn><pos><m><pl>/my<prn><pos><m><pl>$^.<sent>/.<sent>$

|| #Have #lose #two to #the books #my

|-
|10) M'an natu ki su trenu devíat arrivare a sas nove. || They told me that the train was supposed to arrive at nine. || ^Mi<prn><pro><p1><mf><sg>/I<prn><pro><p1><mf><sg>$ ^àere<vbhaver><pri><p3><pl>/have<vbhaver><pri><p3><pl>$ ^nàrrere<vblex><pp><m><sg>/tell<vblex><pp><m><sg>$ ^chi<cnjsub>/that<cnjsub>$ ^su<det><def><m><sg>/the<det><def><m><sg>$ ^trenu<n><m><sg>/train<n><sg>$ ^dèvere<vblex><pii><p3><sg>/shall<vbmod><pii><p3><sg>$ ^arrivare<vblex><inf>/arrive<vblex><inf>$ ^a<pr>/at<pr>/on<pr>/to<pr>$ ^su<det><def><f><pl>/the<det><def><f><pl>$ ^nove<num><mf><sp>/nine<num><mf><sp>$^.<sent>/.<sent>$
|| #I #have #tell that #the train #shall arrive at #the #nine
|
|}

==Additions for polished RBMT system==
*Over 100 new stems to bilingual dictionary
*:(now we have 172 total entries in the .dix file)
*4 sets of lexical selection rules
*:(now we have rules that solve 5 problems in total)
*3 items from contrastive grammar implemented in transfer rules
*:(now we have rules that implement 4 total items)

==expanding lexicon==

{| cellpadding=5
|medas || many || <adj>
|-https://wikis.swarthmore.edu/ling073/index.php?title=Sardinian_and_English&action=edit
|piseddas || girls || <n><pl>
|-
|sun || they are || <v>
|-
|bennidas || to come (home) || <v><pp><fpl>
|-
|balladu || to dance || <v><pp>
|-
|cantaiat || to sing || <v><sg3>
|-
|sos/sa || the || <det>
|-
|piattos || plates || <n><pl>
|-
|mesa || table || <n><sg>
|-
|bi/b' || N/A || <cl>
|-
|problemas || problems || <n><pl>
|-
|unu || one/a || <adj>/<det>
|-
|ube || where || <adv>
|-
|mortu || dead || <v><pp>
|-
|sordatos || soldiers || <n><pl>
|-
|tenimus || we have || <v><pl1>
|-
|frores || flowers || <n><pl>
|-
|keret || to be necessary || <v><sg3>
|-
|mancat || to be missing || <v><sg3>
|-
|ovos || eggs || <n><pl>
|-
|danca || meadow || <n>
|-
|ortu || orchard || <n>
|-
|frade || brother || <n>
|-
|fizza || daughter || <n>
|-
|re || king || <n>
|-
|ora || hour || <n>
|-
|subra || above/on || <prep>
|-
|a || to/at || <prep>
|-
|cumintzos || origins || <n><pl>
|-
|e || and || <conj>
|-
|andamentu || evolution || <n>
|-
|istòricu || historical || <adj>
|-
|de || of/to || <prep>
|-
|sa || the || <det>
|-
|poesia || poetry || <n>
|-
|a bolu || improvised || <adj> (a bolu = improvised, on the fly)
|-
|in || in || <prep>
|-
|sardu || Sardinian || <n>
|-
|logudoresu || Logudorese || <adj>
|-
|non || not || <adv>
|-
|ischit || known || <v><pp>
|-
|meda || much || <adv>
|-
|custu || this || <det><prox>
|-
|artìculu || article || <n>
|-
|chircat || tries || <v><sg3>
|-
|bogare || to bring out || <v>
|-
|pizu || surface || <n> (bogare a pizu = to shed light on, to bring to the surface; see complicated translations of bogare: [http://vocabolariocasu.isresardegna.it/index.php?key=b&int=0&lemmi=cerca&codice=b1264000 here])
|-
|ammentos || memories || <n><pl>
|-
|ammentu || memory || <n>
|-
|ammentare || to remember || <v>
|-
|documentados || documented || <adj>
|-
|si || [null] || <> -- reflexive
|-
|primas || first || <adj>
|-
|disputas || competitions || <n><pl>
|-
|primas || first || <adj>
|-
|tra || between || <prep>
|-
|poetes || poets || <n><pl>
|-
|cale || which || <prn><rel>
|-
|esserent || were || <v> past imperfect 3rd person plural
|-
|règulas || rules, modalities || <n><pl>
|-
|su || the || <det>
|-
|cunfruntu || confrontation || <n>
|-
|sende || being || <v><ger>
|-
|una || a/one || <art>/<adj>
|-
|chirca || research || <n>
|-
|andera || ongoing/progressive || <adj>
|-
|testu || text || <n>
|-
|diat || [null] || <subj><sg3>
|-
|poder || to be able to || <v><inf>
|-
|aer || to have || <v><inf> (also hàere or àere)
|-
|mudonzos || modifications || <n><pl>
|-
|mudonzos || modifications || <n><pl>
|-
|novas || new || <adj><pl>
|-
|noas || data || <n><pl>
|-
|Pro || to || <prep> <-- keep this in mind for lexical selection (to)
|-
|bider || to read || <v><inf>
|-
|artìculu || article || <n>
|-
|sighire || click on || <v><inf>
|-
|intrare || enter || <v><inf>
|-
|desizadu || desired || <adj>
|-
|trenu || train || <n>
|-
|sinke || [null] || <foc>
|-
|fit || was || <v><imp><sg3>
|-
|andande || leaving || <v><ger>
|-
|at || it will || <>
|-
|sas || the || <det>
|-
|deke || ten || <n>
|-
|devet || should || <adv>
|-
|deke || ten || <adj>
|-
|appo || I have || <v><sg1>
|-
|natu || told || <v><pp>
|-
|próere || to rain || <v><inf>
|-
|arrivare || to arrive || <v><inf>
|-
|isco || I know || <v><sg1>
|-
|si || if || <conj>
|-
|ki || that || <conj>
|-
|cras || tomorrow || <adv>
|-
|meos || my || <pos>
|-
|andatos || gone || <adj><pl>
|
|}

===glosses===

Cando so arrivatu a s'istazione, su trenu sink'andaiat

'when I arrived at the station, the train was leaving'

Su trenu sinke fit andande

'The train was leaving"

Su trenu at a arrivare a sas deke

'The train will arrive at ten o'clock'

Su trenu devet arrivare a sas deke

'The train is supposed to arrive at ten o'clock'

T'appo natu ki su trenu diat arrivare a sas deke

'I told you that the train would arrive at ten o'clock'

M'an natu ki su trenu devíat arrivare a sas nove

'They told me that the train was supposed to arrive at nine'

At a próere cras

'It will rain tomorrow'

Devet próere cras

'it is supposed to rain tomorrow'

At a próere cras? Si emmo abbarramus in domo, ma su nono andamus a mare

'Will it rain tomorrow? If so we shall stay at homr, buy if not we will go to the sea'

No'isco si at a próere cras

'I do to know whether it will rain tomorrow'

Una de sas berbekes est maláida

'one of the sheep is sick'

Appo pèrditu duos de sos libros meos

'I have lost two of my books'

Metas de custas pitzinnas sun galanas

'Many of these girls are pretty'

Una pitzinna meta bella

'a very beautiful girl'

Cussas duas bravas pitzinnas

'those two good girls'

unu better cane bellu

'a huge beautiful dog'

un'átteru bette cane

'another huge dog'

Sun andatos a Frantza

'they went to France'

Est ghiratu dae Corsica

'He returned from Corsica'

Connnosco bene sa Frantza

"i know France well'

Custu libru est iscrittu in tedescu

'This book is written in German'

Cussus paráula venit dae su catalanu

'This word comes from Catalan'

Su sardu est una limba antica

'Sardinian is an ancient language'

Appo mandicatu casu

'I ate cheese'

Laura est toddende frores

'Laura is picking flowers'

De frores non nd'appo tódditu

'I did not pick any flowers'

No'amus comporatu pane

'We did not buy bread'

Mandico sa pasta kin casu

'I ate pasta with cheese'

Tres sórrikes an mandicatu tottu su casu

'Three mice ate all the cheese'

semus ponnende vinu in ampullas

'We are putting wine in bottles'

lettu meu esr

'It is my bed'

No'appo lessu libru perunu

'i did not read any book'

Sos k'an furatu si dinari at a èssere punitos

'The people who stole the money will be punished'

Appo invitat sos de Juanne

'I invited Jon's family'

Cussa pinna est sa mea

'That pen is mine'

Cudda mákkina est sa de Juanne

'That car is John's'

Custa ricca at datu mili francos a su vetzu

'This rich woman gave a thousand lira to the old man'

Su guvernu devíat dare ua pensione a dondzi vetzu

'The government should give a pension to every old person'

==Notes for improvement==
*"At" is the third person singular present conjugation of aer, to have.
*It can function as an auxiliary verb when paired with a past participle and thus should be translated as "has" in those cases (e.g. "John has left.").
*When preceding "a" (i.e. "at a [infinitive verb]") it signals future tense: an event will happen, has yet to occur, so it would translate as "has" or "will."
*Another possibility for lexical selection is pro/a/de all translating to "to."
*Make sure "una" in example sentence translates to "a" in English without the hashtag, i.e. get rid of the feminine tag that maps over from the "una" analysis to the English "a" which does not have the feminine tag.
*Disambiguate analyses of "deke" (ten): is it noun or adjective? (I guess this might just be morphological disambiguation and not lexical selection)
*Fix tags for past participle of told/tell

==External Resources==

*Github repository for [https://github.com/apertium/apertium-srd Sardinian transducer] (and our [https://github.swarthmore.edu/Ling073-sp23/ling073-srd clone])
*Github repository for [https://github.com/apertium/apertium-eng English transducer]
*[https://www.limbasardasudsardigna.it/sar/images/Documenti/Didatica_e_Ainas/Ditzion%C3%A0riu%20Universale%20Rubattu.pdf Dictionary pdf]
*[http://ditzionariu.sardegnacultura.it/it/ Online official dictionary]
*[https://it.glosbe.com/sc/it Web-based machine translator]
*[http://vocabolariocasu.isresardegna.it/index.php?key=a&int=0&lemmi=cerca Sardinian-Italian web-based dictionary]
*[http://www.sardegnadigitallibrary.it/mmt/fullsize/2009050512495700047.pdf 1931 pdf with select translations]
*[https://onlinelibrary.wiley.com/doi/epdf/10.1111/j.0079-1636.2004.00130.x Definiteness effects: evidence from Sardinian]
*[https://www.icongrouponline.com/en/Detail/dictionary/049783698X/Webster%27s+Sardinian+-+English+Thesaurus+Dictionary: Webster's Sardinian English Thesaurus Dictionary]
*[https://www.academia.edu/15320922/Dizionario_della_lingua_Sarda_Vol_2 Italian-Sardinian Dictionary]
*[https://archive.org/details/vocabolariosardo00spanuoft/page/n361/mode/2up Old but extensive Sardo-Italian and vice versa dictionary]
*[https://limbasardasudsardigna.it/sar/images/Documenti/Didatica_e_Ainas/Vocabolariu_Sardu_Italianu_Spano.pdf nice Sardo-Italiano dictionary pdf]
*[http://www.fontesarda.it/sr/sr0045.htm Conjugations of "to have" in Sardinian]
*[https://sinnainotizie.com/2015/03/07/lezioni-di-grammatica-sardo-campidanese-undicesima-lezione-su-verbu-ai-aere/ Whole Sardinian grammar page about conjugations of to have all written in Sardinian language!]
*Sardinian grammar:[https://www.limbasardasudsardigna.it/sar/images/Documenti/Didatica_e_Ainas/grammatiga_sardo%20campidanese%20A.LEPORI.pdf pdf]
[[Category:Sp23_TranslationPairs]],[[Category:Sardinian]],[[Category:English]]

Sardinian and English/Structural transfer

2023-05-04T16:10:21Z

Rorlija1: /* post evaluation */

Sardinian and English/Structural transfer

2023-05-04T15:58:43Z

Rorlija1: /* Item 3: Posessive determiner/marker order in noun phraseology */

Sardinian and English/Structural transfer output

2023-05-04T15:57:46Z

Rorlija1: /* For Item 2: Noun-adjective order in noun phraseology: adjectives now come before the noun in translations when necessary: */

Given that the output of the srd-eng-transfer is quite lengthy in some instances, I've opted to create this page to reduce clutter on [https://wikis.swarthmore.edu/ling073/Sardinian_and_English/Structural_transfer the main structural transfer page].

==For '''Item 1: Determiners before nouns in Sardinian are omitted in English translations that do not include determiners before nouns'''==

Applying rule 5 (line 61): ^Su<det><def><f><sg>/The<det><def><f><sg>$ ^Frantza<np><top><f><sg>/France<np><top><f><sg>$

Applying rule 6 (line 63): ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$

Applying rule 11 (line 69): ^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$

Applying rule 12 (line 71): ^Default<DP><PD><ND>{^Su<det><def><f><sg>/The<det><def><f><sg>$ ^Frantza<np><top><f><sg>/France<np><top><f><sg>$}$ ^be<VP><p3><sg>{^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$}$

Applying rule 3 (line 58): ^paisu<n><m><sg>/country<n><sg>$

Applying rule 4 (line 60): ^unu<det><ind><m><sg>/a<det><ind><m><sg>$ ^default<NP><PD><ND>{^paisu<n><m><sg>/country<n><sg>$}$

Applying rule 9 (line 67): ^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><m><sg>/a<det><ind><m><sg>$ ^default<NP><PD><ND>{^paisu<n><m><sg>/country<n><sg>$}$}$

Applying rule 12 (line 71): ^Default<DP><PD><ND>{^Su<det><def><f><sg>/The<det><def><f><sg>$ ^Frantza<np><top><f><sg>/France<np><top><f><sg>$}$ ^be<VP><p3><sg>{^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><m><sg>/a<det><ind><m><sg>$ ^default<NP><PD><ND>{^paisu<n><m><sg>/country<n><sg>$}$}$}$

Applying rule 1 (line 56): ^paisu<n><m><sg>/country<n><sg>$ ^bellu<adj><m><sg>/beautiful<adj><m><sg>$

Applying rule 4 (line 60): ^unu<det><ind><m><sg>/a<det><ind><m><sg>$ ^default<NP><PD><ND>{^paisu<n><m><sg>/country<n><sg>$ ^bellu<adj><m><sg>/beautiful<adj><m><sg>$}$

Applying rule 9 (line 67): ^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><m><sg>/a<det><ind><m><sg>$ ^default<NP><PD><ND>{^paisu<n><m><sg>/country<n><sg>$ ^bellu<adj><m><sg>/beautiful<adj><m><sg>$}$}$

Applying rule 12 (line 71): ^Default<DP><PD><ND>{^Su<det><def><f><sg>/The<det><def><f><sg>$ ^Frantza<np><top><f><sg>/France<np><top><f><sg>$}$ ^be<VP><p3><sg>{^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><m><sg>/a<det><ind><m><sg>$ ^default<NP><PD><ND>{^paisu<n><m><sg>/country<n><sg>$ ^bellu<adj><m><sg>/beautiful<adj><m><sg>$}$}$}$

Applying output rule 11 (line 71): Be<#S><p3><sg> -> ^Default<DP><PD><ND>{^Su<det><def><f><sg>/The<det><def><f><sg>$ ^Frantza<np><top><f><sg>/France<np><top><f><sg>$}$ ^be<VP><p3><sg>{^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><m><sg>/a<det><ind><m><sg>$ ^default<NP><PD><ND>{^paisu<n><m><sg>/country<n><sg>$ ^bellu<adj><m><sg>/beautiful<adj><m><sg>$}$}$}$

Applying output rule 4 (line 61): Default<DP><p3><sg> -> ^Su<det><def><f><sg>/The<det><def><f><sg>$ ^Frantza<np><top><f><sg>/France<np><top><f><sg>$

No rule specified: ^France<np><top><sg>$

Applying output rule 8 (line 67): be<VP><p3><sg> -> ^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><m><sg>/a<det><ind><m><sg>$ ^default<NP><PD><ND>{^paisu<n><m><sg>/country<n><sg>$ ^bellu<adj><m><sg>/beautiful<adj><m><sg>$}$}$

Applying output rule 5 (line 63): be<vP><p3><sg> -> ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$

No rule specified: ^be<vbser><pres><p3><sg>$

Applying output rule 3 (line 60): default<DP><p3><sg> -> ^unu<det><ind><m><sg>/a<det><ind><m><sg>$ ^default<NP><PD><ND>{^paisu<n><m><sg>/country<n><sg>$ ^bellu<adj><m><sg>/beautiful<adj><m><sg>$}$

No rule specified: ^a<det><ind><sg>$

Applying output rule 0 (line 56): default<NP><p3><sg> -> ^paisu<n><m><sg>/country<n><sg>$ ^bellu<adj><m><sg>/beautiful<adj><m><sg>$

No rule specified: ^beautiful<adj>$

No rule specified: ^country<n><sg>$

No rule specified: ^.<sent>/.<sent>$

No rule specified: ^.<sent>/.<sent>$
^France<np><top><sg>$ ^be<vbser><pres><p3><sg>$ ^a<det><ind><sg>$ ^beautiful<adj>$ ^country<n><sg>$^.<sent>$^.<sent>$

==For '''Item 2: Noun-adjective order in noun phraseology: adjectives now come before the noun in translations when necessary:'''==

Applying rule 3 (line 58): ^sardu<n><m><sg>/Sardinian<n><sg>$

Applying rule 4 (line 60): ^Su<det><def><m><sg>/The<det><def><m><sg>$ ^Default<NP><PD><ND>{^sardu<n><m><sg>/Sardinian<n><sg>$}$

Applying rule 6 (line 63): ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$

Applying rule 11 (line 69): ^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$

Applying rule 12 (line 71): ^Default<DP><PD><ND>{^Su<det><def><m><sg>/The<det><def><m><sg>$ ^Default<NP><PD><ND>{^sardu<n><m><sg>/Sardinian<n><sg>$}$}$ ^be<VP><p3><sg>{^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$}$

Applying rule 6 (line 63): ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$

Applying rule 11 (line 69): ^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$

Applying rule 13 (line 72): ^Default<NP><PD><ND>{^sardu<n><m><sg>/Sardinian<n><sg>$}$ ^be<VP><p3><sg>{^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$}$

Applying rule 3 (line 58): ^limba<n><f><sg>/language<n><sg>$

Applying rule 4 (line 60): ^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$}$

Applying rule 9 (line 67): ^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$}$}$

Applying rule 12 (line 71): ^Default<DP><PD><ND>{^Su<det><def><m><sg>/The<det><def><m><sg>$ ^Default<NP><PD><ND>{^sardu<n><m><sg>/Sardinian<n><sg>$}$}$ ^be<VP><p3><sg>{^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$}$}$}$

Applying rule 3 (line 58): ^limba<n><f><sg>/language<n><sg>$

Applying rule 4 (line 60): ^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$}$

Applying rule 9 (line 67): ^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$}$}$

Applying rule 13 (line 72): ^Default<NP><PD><ND>{^sardu<n><m><sg>/Sardinian<n><sg>$}$ ^be<VP><p3><sg>{^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$}$}$}$

Applying rule 1 (line 56): ^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$

Applying rule 4 (line 60): ^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$}$

Applying rule 9 (line 67): ^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$}$}$

Applying rule 12 (line 71): ^Default<DP><PD><ND>{^Su<det><def><m><sg>/The<det><def><m><sg>$ ^Default<NP><PD><ND>{^sardu<n><m><sg>/Sardinian<n><sg>$}$}$ ^be<VP><p3><sg>{^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$}$}$}$

Applying rule 1 (line 56): ^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$

Applying rule 4 (line 60): ^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$}$

Applying rule 9 (line 67): ^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$}$}$

Applying rule 13 (line 72): ^Default<NP><PD><ND>{^sardu<n><m><sg>/Sardinian<n><sg>$}$ ^be<VP><p3><sg>{^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$}$}$}$

Applying output rule 11 (line 71): Be<#S><p3><sg> -> ^Default<DP><PD><ND>{^Su<det><def><m><sg>/The<det><def><m><sg>$ ^Default<NP><PD><ND>{^sardu<n><m><sg>/Sardinian<n><sg>$}$}$ ^be<VP><p3><sg>{^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$}$}$}$

Applying output rule 3 (line 60): Default<DP><p3><sg> -> ^Su<det><def><m><sg>/The<det><def><m><sg>$ ^Default<NP><PD><ND>{^sardu<n><m><sg>/Sardinian<n><sg>$}$

No rule specified: ^The<det><def><sg>$

Applying output rule 2 (line 58): Default<NP><p3><sg> -> ^sardu<n><m><sg>/Sardinian<n><sg>$

No rule specified: ^Sardinian<n><sg>$

Applying output rule 8 (line 67): be<VP><p3><sg> -> ^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$}$}$

Applying output rule 5 (line 63): be<vP><p3><sg> -> ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$

No rule specified: ^be<vbser><pres><p3><sg>$

Applying output rule 3 (line 60): default<DP><p3><sg> -> ^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$}$

No rule specified: ^a<det><ind><sg>$

Applying output rule 0 (line 56): default<NP><p3><sg> -> ^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$

No rule specified: ^ancient<adj>$

No rule specified: ^language<n><sg>$

No rule specified: ^.<sent>/.<sent>$

No rule specified: ^.<sent>/.<sent>$
^The<det><def><sg>$ ^Sardinian<n><sg>$ ^be<vbser><pres><p3><sg>$ ^a<det><ind><sg>$ ^ancient<adj>$ ^language<n><sg>$^.<sent>$^.<sent>$

==For '''Item 3: Posessive determiner/marker order in noun phraseology'''==

Applying rule 3 (line 58): ^Libru<n><m><sg>/Book<n><sg>$
Applying rule 1 (line 56): ^Libru<n><m><sg>/Book<n><sg>$ ^meu<adj><pos><m><sg>/my<det><pos><m><sg>$
Applying rule 6 (line 63): ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$
Applying rule 11 (line 69): ^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$
Applying rule 13 (line 72): ^Default<NP><PD><ND>{^Libru<n><m><sg>/Book<n><sg>$ ^meu<adj><pos><m><sg>/my<det><pos><m><sg>$}$ ^be<VP><p3><sg>{^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$}$
Applying output rule 12 (line 72): Be<#S><p3><sg> -> ^Default<NP><PD><ND>{^Libru<n><m><sg>/Book<n><sg>$ ^meu<adj><pos><m><sg>/my<det><pos><m><sg>$}$ ^be<VP><p3><sg>{^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$}$
Applying output rule 0 (line 56): Default<NP><p3><sg> -> ^Libru<n><m><sg>/Book<n><sg>$ ^meu<adj><pos><m><sg>/my<det><pos><m><sg>$
No rule specified: ^my<det>$
No rule specified: ^Book<n><sg>$
Applying output rule 10 (line 69): be<VP><p3><sg> -> ^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$
Applying output rule 5 (line 63): be<vP><p3><sg> -> ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$
No rule specified: ^be<vbser><pres><p3><sg>$
No rule specified: ^.<sent>/.<sent>$
No rule specified: ^.<sent>/.<sent>$
^my<det>$ ^Book<n><sg>$ ^be<vbser><pres><p3><sg>$^.<sent>$^.<sent>$

==For '''Item 4: For most uses/conjugations of verbs in Sardinian, the verb stands on its own without a personal pronoun, while in English personal pronouns always precede any conjugated verbs. In other words, the tags of "appo" (I have) determine a new word "I" which precedes "have" in the English translation.'''==

Applying rule 7 (line 64): ^Àere<vbhaver><pri><p1><sg>/Have<vbhaver><pri><p1><sg>$
Applying rule 11 (line 69): ^Have<vP><p1><sg>{^Àere<vbhaver><pri><p1><sg>/Have<vbhaver><pri><p1><sg>$}$
Applying rule 15 (line 74): ^Have<VP><p1><sg>{^Have<vP><p1><sg>{^Àere<vbhaver><pri><p1><sg>/Have<vbhaver><pri><p1><sg>$}$}$
Applying rule 8 (line 65): ^pèrdere<vblex><pp><m><sg>/lose<vblex><pp><m><sg>$
Applying rule 10 (line 68): ^Have<vP><p1><sg>{^Àere<vbhaver><pri><p1><sg>/Have<vbhaver><pri><p1><sg>$}$ ^lose<vP><PD><sg>{^pèrdere<vblex><pp><m><sg>/lose<vblex><pp><m><sg>$}$
Applying rule 15 (line 74): ^Have<VP><p1><sg>{^Have<vP><p1><sg>{^Àere<vbhaver><pri><p1><sg>/Have<vbhaver><pri><p1><sg>$}$ ^lose<vP><PD><sg>{^pèrdere<vblex><pp><m><sg>/lose<vblex><pp><m><sg>$}$}$
Applying output rule 14 (line 74): Have<#S><p1><sg> -> ^Have<VP><p1><sg>{^Have<vP><p1><sg>{^Àere<vbhaver><pri><p1><sg>/Have<vbhaver><pri><p1><sg>$}$ ^lose<vP><PD><sg>{^pèrdere<vblex><pp><m><sg>/lose<vblex><pp><m><sg>$}$}$
No rule specified: ^prpers<prn><subj><p1><mf><sg>$
Applying output rule 9 (line 68): Have<VP><p1><sg> -> ^Have<vP><p1><sg>{^Àere<vbhaver><pri><p1><sg>/Have<vbhaver><pri><p1><sg>$}$ ^lose<vP><PD><sg>{^pèrdere<vblex><pp><m><sg>/lose<vblex><pp><m><sg>$}$
Applying output rule 6 (line 64): Have<vP><p1><sg> -> ^Àere<vbhaver><pri><p1><sg>/Have<vbhaver><pri><p1><sg>$
No rule specified: ^Have<vbhaver><pres><p1><sg>$=
Applying output rule 7 (line 65): lose<vP><p3><sg> -> ^pèrdere<vblex><pp><m><sg>/lose<vblex><pp><m><sg>$
No rule specified: ^lose<vblex><p3><sg>$
No rule specified: ^duos<num><m><sp>/two<num><m><sp>$
No rule specified: ^de<pr>/of<pr>$
Applying rule 3 (line 58): ^libru<n><m><pl>/book<n><pl>$
Applying rule 4 (line 60): ^su<det><def><m><pl>/the<det><def><m><pl>$ ^default<NP><PD><ND>{^libru<n><m><pl>/book<n><pl>$}$
Applying rule 1 (line 56): ^libru<n><m><pl>/book<n><pl>$ ^meu<adj><pos><m><pl>/my<det><pos><m><pl>$
Applying rule 4 (line 60): ^su<det><def><m><pl>/the<det><def><m><pl>$ ^default<NP><PD><ND>{^libru<n><m><pl>/book<n><pl>$ ^meu<adj><pos><m><pl>/my<det><pos><m><pl>$}$
Applying output rule 3 (line 60): default<DP><PD><ND> -> ^su<det><def><m><pl>/the<det><def><m><pl>$ ^default<NP><PD><ND>{^libru<n><m><pl>/book<n><pl>$ ^meu<adj><pos><m><pl>/my<det><pos><m><pl>$}$
No rule specified: ^the<det><def><pl>$
Applying output rule 0 (line 56): default<NP><p3><sg> -> ^libru<n><m><pl>/book<n><pl>$ ^meu<adj><pos><m><pl>/my<det><pos><m><pl>$
No rule specified: ^my<det>$

[[Category:Sp23_StructuralTransfer]],[[Category:Sardinian]],[[Category:English]]
No rule specified: ^book<n><pl>$
No rule specified: ^.<sent>/.<sent>$
No rule specified: ^.<sent>/.<sent>$
^prpers<prn><subj><p1><mf><sg>$ ^Have<vbhaver><pres><p1><sg>$ ^lose<vblex><p3><sg>$ ^two<num><m><sp>$ ^of<pr>$ ^the<det><def><pl>$ ^my<det>$ ^book<n><pl>$^.<sent>$^.<sent>$

Sardinian and English/Structural transfer

2023-05-04T15:55:22Z

Rorlija1: /* post evaluation */

Sardinian and English/Structural transfer output

2023-05-04T15:41:38Z

Rorlija1:

Given that the output of the srd-eng-transfer is quite lengthy in some instances, I've opted to create this page to reduce clutter on [https://wikis.swarthmore.edu/ling073/Sardinian_and_English/Structural_transfer the main structural transfer page].

==For '''Item 1: Determiners before nouns in Sardinian are omitted in English translations that do not include determiners before nouns'''==

Applying rule 5 (line 61): ^Su<det><def><f><sg>/The<det><def><f><sg>$ ^Frantza<np><top><f><sg>/France<np><top><f><sg>$

Applying rule 6 (line 63): ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$

Applying rule 11 (line 69): ^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$

Applying rule 12 (line 71): ^Default<DP><PD><ND>{^Su<det><def><f><sg>/The<det><def><f><sg>$ ^Frantza<np><top><f><sg>/France<np><top><f><sg>$}$ ^be<VP><p3><sg>{^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$}$

Applying rule 3 (line 58): ^paisu<n><m><sg>/country<n><sg>$

Applying rule 4 (line 60): ^unu<det><ind><m><sg>/a<det><ind><m><sg>$ ^default<NP><PD><ND>{^paisu<n><m><sg>/country<n><sg>$}$

Applying rule 9 (line 67): ^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><m><sg>/a<det><ind><m><sg>$ ^default<NP><PD><ND>{^paisu<n><m><sg>/country<n><sg>$}$}$

Applying rule 12 (line 71): ^Default<DP><PD><ND>{^Su<det><def><f><sg>/The<det><def><f><sg>$ ^Frantza<np><top><f><sg>/France<np><top><f><sg>$}$ ^be<VP><p3><sg>{^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><m><sg>/a<det><ind><m><sg>$ ^default<NP><PD><ND>{^paisu<n><m><sg>/country<n><sg>$}$}$}$

Applying rule 1 (line 56): ^paisu<n><m><sg>/country<n><sg>$ ^bellu<adj><m><sg>/beautiful<adj><m><sg>$

Applying rule 4 (line 60): ^unu<det><ind><m><sg>/a<det><ind><m><sg>$ ^default<NP><PD><ND>{^paisu<n><m><sg>/country<n><sg>$ ^bellu<adj><m><sg>/beautiful<adj><m><sg>$}$

Applying rule 9 (line 67): ^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><m><sg>/a<det><ind><m><sg>$ ^default<NP><PD><ND>{^paisu<n><m><sg>/country<n><sg>$ ^bellu<adj><m><sg>/beautiful<adj><m><sg>$}$}$

Applying rule 12 (line 71): ^Default<DP><PD><ND>{^Su<det><def><f><sg>/The<det><def><f><sg>$ ^Frantza<np><top><f><sg>/France<np><top><f><sg>$}$ ^be<VP><p3><sg>{^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><m><sg>/a<det><ind><m><sg>$ ^default<NP><PD><ND>{^paisu<n><m><sg>/country<n><sg>$ ^bellu<adj><m><sg>/beautiful<adj><m><sg>$}$}$}$

Applying output rule 11 (line 71): Be<#S><p3><sg> -> ^Default<DP><PD><ND>{^Su<det><def><f><sg>/The<det><def><f><sg>$ ^Frantza<np><top><f><sg>/France<np><top><f><sg>$}$ ^be<VP><p3><sg>{^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><m><sg>/a<det><ind><m><sg>$ ^default<NP><PD><ND>{^paisu<n><m><sg>/country<n><sg>$ ^bellu<adj><m><sg>/beautiful<adj><m><sg>$}$}$}$

Applying output rule 4 (line 61): Default<DP><p3><sg> -> ^Su<det><def><f><sg>/The<det><def><f><sg>$ ^Frantza<np><top><f><sg>/France<np><top><f><sg>$

No rule specified: ^France<np><top><sg>$

Applying output rule 8 (line 67): be<VP><p3><sg> -> ^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><m><sg>/a<det><ind><m><sg>$ ^default<NP><PD><ND>{^paisu<n><m><sg>/country<n><sg>$ ^bellu<adj><m><sg>/beautiful<adj><m><sg>$}$}$

Applying output rule 5 (line 63): be<vP><p3><sg> -> ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$

No rule specified: ^be<vbser><pres><p3><sg>$

Applying output rule 3 (line 60): default<DP><p3><sg> -> ^unu<det><ind><m><sg>/a<det><ind><m><sg>$ ^default<NP><PD><ND>{^paisu<n><m><sg>/country<n><sg>$ ^bellu<adj><m><sg>/beautiful<adj><m><sg>$}$

No rule specified: ^a<det><ind><sg>$

Applying output rule 0 (line 56): default<NP><p3><sg> -> ^paisu<n><m><sg>/country<n><sg>$ ^bellu<adj><m><sg>/beautiful<adj><m><sg>$

No rule specified: ^beautiful<adj>$

No rule specified: ^country<n><sg>$

No rule specified: ^.<sent>/.<sent>$

No rule specified: ^.<sent>/.<sent>$
^France<np><top><sg>$ ^be<vbser><pres><p3><sg>$ ^a<det><ind><sg>$ ^beautiful<adj>$ ^country<n><sg>$^.<sent>$^.<sent>$

==For '''Item 2: Noun-adjective order in noun phraseology: adjectives now come before the noun in translations when necessary:'''==

Applying rule 3 (line 58): ^sardu<n><m><sg>/Sardinian<n><sg>$

Applying rule 4 (line 60): ^Su<det><def><m><sg>/The<det><def><m><sg>$ ^Default<NP><PD><ND>{^sardu<n><m><sg>/Sardinian<n><sg>$}$

Applying rule 6 (line 63): ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$

Applying rule 11 (line 69): ^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$

Applying rule 12 (line 71): ^Default<DP><PD><ND>{^Su<det><def><m><sg>/The<det><def><m><sg>$ ^Default<NP><PD><ND>{^sardu<n><m><sg>/Sardinian<n><sg>$}$}$ ^be<VP><p3><sg>{^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$}$

Applying rule 6 (line 63): ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$

Applying rule 11 (line 69): ^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$

Applying rule 13 (line 72): ^Default<NP><PD><ND>{^sardu<n><m><sg>/Sardinian<n><sg>$}$ ^be<VP><p3><sg>{^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$}$

Applying rule 3 (line 58): ^limba<n><f><sg>/language<n><sg>$

Applying rule 4 (line 60): ^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$}$

Applying rule 9 (line 67): ^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$}$}$

Applying rule 12 (line 71): ^Default<DP><PD><ND>{^Su<det><def><m><sg>/The<det><def><m><sg>$ ^Default<NP><PD><ND>{^sardu<n><m><sg>/Sardinian<n><sg>$}$}$ ^be<VP><p3><sg>{^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$}$}$}$

Applying rule 3 (line 58): ^limba<n><f><sg>/language<n><sg>$

Applying rule 4 (line 60): ^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$}$

Applying rule 9 (line 67): ^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$}$}$

Applying rule 13 (line 72): ^Default<NP><PD><ND>{^sardu<n><m><sg>/Sardinian<n><sg>$}$ ^be<VP><p3><sg>{^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$}$}$}$

Applying rule 1 (line 56): ^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$

Applying rule 4 (line 60): ^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$}$

Applying rule 9 (line 67): ^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$}$}$

Applying rule 12 (line 71): ^Default<DP><PD><ND>{^Su<det><def><m><sg>/The<det><def><m><sg>$ ^Default<NP><PD><ND>{^sardu<n><m><sg>/Sardinian<n><sg>$}$}$ ^be<VP><p3><sg>{^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$}$}$}$

Applying rule 1 (line 56): ^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$

Applying rule 4 (line 60): ^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$}$

Applying rule 9 (line 67): ^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$}$}$

Applying rule 13 (line 72): ^Default<NP><PD><ND>{^sardu<n><m><sg>/Sardinian<n><sg>$}$ ^be<VP><p3><sg>{^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$}$}$}$

Applying output rule 11 (line 71): Be<#S><p3><sg> -> ^Default<DP><PD><ND>{^Su<det><def><m><sg>/The<det><def><m><sg>$ ^Default<NP><PD><ND>{^sardu<n><m><sg>/Sardinian<n><sg>$}$}$ ^be<VP><p3><sg>{^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$}$}$}$

Applying output rule 3 (line 60): Default<DP><p3><sg> -> ^Su<det><def><m><sg>/The<det><def><m><sg>$ ^Default<NP><PD><ND>{^sardu<n><m><sg>/Sardinian<n><sg>$}$

No rule specified: ^The<det><def><sg>$

Applying output rule 2 (line 58): Default<NP><p3><sg> -> ^sardu<n><m><sg>/Sardinian<n><sg>$

No rule specified: ^Sardinian<n><sg>$

Applying output rule 8 (line 67): be<VP><p3><sg> -> ^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$}$}$

Applying output rule 5 (line 63): be<vP><p3><sg> -> ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$

No rule specified: ^be<vbser><pres><p3><sg>$

Applying output rule 3 (line 60): default<DP><p3><sg> -> ^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$}$

No rule specified: ^a<det><ind><sg>$

Applying output rule 0 (line 56): default<NP><p3><sg> -> ^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$

No rule specified: ^ancient<adj>$

No rule specified: ^language<n><sg>$

No rule specified: ^.<sent>/.<sent>$

No rule specified: ^.<sent>/.<sent>$
^The<det><def><sg>$ ^Sardinian<n><sg>$ ^be<vbser><pres><p3><sg>$ ^a<det><ind><sg>$ ^ancient<adj>$ ^language<n><sg>$^.<sent>$^.<sent>$

==For '''Item 4: For most uses/conjugations of verbs in Sardinian, the verb stands on its own without a personal pronoun, while in English personal pronouns always precede any conjugated verbs. In other words, the tags of "appo" (I have) determine a new word "I" which precedes "have" in the English translation.'''==

Applying rule 7 (line 64): ^Àere<vbhaver><pri><p1><sg>/Have<vbhaver><pri><p1><sg>$
Applying rule 11 (line 69): ^Have<vP><p1><sg>{^Àere<vbhaver><pri><p1><sg>/Have<vbhaver><pri><p1><sg>$}$
Applying rule 15 (line 74): ^Have<VP><p1><sg>{^Have<vP><p1><sg>{^Àere<vbhaver><pri><p1><sg>/Have<vbhaver><pri><p1><sg>$}$}$
Applying rule 8 (line 65): ^pèrdere<vblex><pp><m><sg>/lose<vblex><pp><m><sg>$
Applying rule 10 (line 68): ^Have<vP><p1><sg>{^Àere<vbhaver><pri><p1><sg>/Have<vbhaver><pri><p1><sg>$}$ ^lose<vP><PD><sg>{^pèrdere<vblex><pp><m><sg>/lose<vblex><pp><m><sg>$}$
Applying rule 15 (line 74): ^Have<VP><p1><sg>{^Have<vP><p1><sg>{^Àere<vbhaver><pri><p1><sg>/Have<vbhaver><pri><p1><sg>$}$ ^lose<vP><PD><sg>{^pèrdere<vblex><pp><m><sg>/lose<vblex><pp><m><sg>$}$}$
Applying output rule 14 (line 74): Have<#S><p1><sg> -> ^Have<VP><p1><sg>{^Have<vP><p1><sg>{^Àere<vbhaver><pri><p1><sg>/Have<vbhaver><pri><p1><sg>$}$ ^lose<vP><PD><sg>{^pèrdere<vblex><pp><m><sg>/lose<vblex><pp><m><sg>$}$}$
No rule specified: ^prpers<prn><subj><p1><mf><sg>$
Applying output rule 9 (line 68): Have<VP><p1><sg> -> ^Have<vP><p1><sg>{^Àere<vbhaver><pri><p1><sg>/Have<vbhaver><pri><p1><sg>$}$ ^lose<vP><PD><sg>{^pèrdere<vblex><pp><m><sg>/lose<vblex><pp><m><sg>$}$
Applying output rule 6 (line 64): Have<vP><p1><sg> -> ^Àere<vbhaver><pri><p1><sg>/Have<vbhaver><pri><p1><sg>$
No rule specified: ^Have<vbhaver><pres><p1><sg>$=
Applying output rule 7 (line 65): lose<vP><p3><sg> -> ^pèrdere<vblex><pp><m><sg>/lose<vblex><pp><m><sg>$
No rule specified: ^lose<vblex><p3><sg>$
No rule specified: ^duos<num><m><sp>/two<num><m><sp>$
No rule specified: ^de<pr>/of<pr>$
Applying rule 3 (line 58): ^libru<n><m><pl>/book<n><pl>$
Applying rule 4 (line 60): ^su<det><def><m><pl>/the<det><def><m><pl>$ ^default<NP><PD><ND>{^libru<n><m><pl>/book<n><pl>$}$
Applying rule 1 (line 56): ^libru<n><m><pl>/book<n><pl>$ ^meu<adj><pos><m><pl>/my<det><pos><m><pl>$
Applying rule 4 (line 60): ^su<det><def><m><pl>/the<det><def><m><pl>$ ^default<NP><PD><ND>{^libru<n><m><pl>/book<n><pl>$ ^meu<adj><pos><m><pl>/my<det><pos><m><pl>$}$
Applying output rule 3 (line 60): default<DP><PD><ND> -> ^su<det><def><m><pl>/the<det><def><m><pl>$ ^default<NP><PD><ND>{^libru<n><m><pl>/book<n><pl>$ ^meu<adj><pos><m><pl>/my<det><pos><m><pl>$}$
No rule specified: ^the<det><def><pl>$
Applying output rule 0 (line 56): default<NP><p3><sg> -> ^libru<n><m><pl>/book<n><pl>$ ^meu<adj><pos><m><pl>/my<det><pos><m><pl>$
No rule specified: ^my<det>$

[[Category:Sp23_StructuralTransfer]],[[Category:Sardinian]],[[Category:English]]
No rule specified: ^book<n><pl>$
No rule specified: ^.<sent>/.<sent>$
No rule specified: ^.<sent>/.<sent>$
^prpers<prn><subj><p1><mf><sg>$ ^Have<vbhaver><pres><p1><sg>$ ^lose<vblex><p3><sg>$ ^two<num><m><sp>$ ^of<pr>$ ^the<det><def><pl>$ ^my<det>$ ^book<n><pl>$^.<sent>$^.<sent>$

Sardinian and English/Structural transfer output

2023-05-04T15:41:14Z

Rorlija1: /* For Item 4: For most uses/conjugations of verbs in Sardinian, the verb stands on its own without a personal pronoun, while in English personal pronouns always precede any conjugated verbs. In other words, the tags of "appo" (I have) determine a new...

Given that the output of the srd-eng-transfer is quite lengthy in some instances, I've opted to create this page to reduce clutter on the main structural transfer page.

==For '''Item 1: Determiners before nouns in Sardinian are omitted in English translations that do not include determiners before nouns'''==

Applying rule 5 (line 61): ^Su<det><def><f><sg>/The<det><def><f><sg>$ ^Frantza<np><top><f><sg>/France<np><top><f><sg>$

Applying rule 6 (line 63): ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$

Applying rule 11 (line 69): ^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$

Applying rule 12 (line 71): ^Default<DP><PD><ND>{^Su<det><def><f><sg>/The<det><def><f><sg>$ ^Frantza<np><top><f><sg>/France<np><top><f><sg>$}$ ^be<VP><p3><sg>{^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$}$

Applying rule 3 (line 58): ^paisu<n><m><sg>/country<n><sg>$

Applying rule 4 (line 60): ^unu<det><ind><m><sg>/a<det><ind><m><sg>$ ^default<NP><PD><ND>{^paisu<n><m><sg>/country<n><sg>$}$

Applying rule 9 (line 67): ^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><m><sg>/a<det><ind><m><sg>$ ^default<NP><PD><ND>{^paisu<n><m><sg>/country<n><sg>$}$}$

Applying rule 12 (line 71): ^Default<DP><PD><ND>{^Su<det><def><f><sg>/The<det><def><f><sg>$ ^Frantza<np><top><f><sg>/France<np><top><f><sg>$}$ ^be<VP><p3><sg>{^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><m><sg>/a<det><ind><m><sg>$ ^default<NP><PD><ND>{^paisu<n><m><sg>/country<n><sg>$}$}$}$

Applying rule 1 (line 56): ^paisu<n><m><sg>/country<n><sg>$ ^bellu<adj><m><sg>/beautiful<adj><m><sg>$

Applying rule 4 (line 60): ^unu<det><ind><m><sg>/a<det><ind><m><sg>$ ^default<NP><PD><ND>{^paisu<n><m><sg>/country<n><sg>$ ^bellu<adj><m><sg>/beautiful<adj><m><sg>$}$

Applying rule 9 (line 67): ^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><m><sg>/a<det><ind><m><sg>$ ^default<NP><PD><ND>{^paisu<n><m><sg>/country<n><sg>$ ^bellu<adj><m><sg>/beautiful<adj><m><sg>$}$}$

Applying rule 12 (line 71): ^Default<DP><PD><ND>{^Su<det><def><f><sg>/The<det><def><f><sg>$ ^Frantza<np><top><f><sg>/France<np><top><f><sg>$}$ ^be<VP><p3><sg>{^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><m><sg>/a<det><ind><m><sg>$ ^default<NP><PD><ND>{^paisu<n><m><sg>/country<n><sg>$ ^bellu<adj><m><sg>/beautiful<adj><m><sg>$}$}$}$

Applying output rule 11 (line 71): Be<#S><p3><sg> -> ^Default<DP><PD><ND>{^Su<det><def><f><sg>/The<det><def><f><sg>$ ^Frantza<np><top><f><sg>/France<np><top><f><sg>$}$ ^be<VP><p3><sg>{^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><m><sg>/a<det><ind><m><sg>$ ^default<NP><PD><ND>{^paisu<n><m><sg>/country<n><sg>$ ^bellu<adj><m><sg>/beautiful<adj><m><sg>$}$}$}$

Applying output rule 4 (line 61): Default<DP><p3><sg> -> ^Su<det><def><f><sg>/The<det><def><f><sg>$ ^Frantza<np><top><f><sg>/France<np><top><f><sg>$

No rule specified: ^France<np><top><sg>$

Applying output rule 8 (line 67): be<VP><p3><sg> -> ^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><m><sg>/a<det><ind><m><sg>$ ^default<NP><PD><ND>{^paisu<n><m><sg>/country<n><sg>$ ^bellu<adj><m><sg>/beautiful<adj><m><sg>$}$}$

Applying output rule 5 (line 63): be<vP><p3><sg> -> ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$

No rule specified: ^be<vbser><pres><p3><sg>$

Applying output rule 3 (line 60): default<DP><p3><sg> -> ^unu<det><ind><m><sg>/a<det><ind><m><sg>$ ^default<NP><PD><ND>{^paisu<n><m><sg>/country<n><sg>$ ^bellu<adj><m><sg>/beautiful<adj><m><sg>$}$

No rule specified: ^a<det><ind><sg>$

Applying output rule 0 (line 56): default<NP><p3><sg> -> ^paisu<n><m><sg>/country<n><sg>$ ^bellu<adj><m><sg>/beautiful<adj><m><sg>$

No rule specified: ^beautiful<adj>$

No rule specified: ^country<n><sg>$

No rule specified: ^.<sent>/.<sent>$

No rule specified: ^.<sent>/.<sent>$
^France<np><top><sg>$ ^be<vbser><pres><p3><sg>$ ^a<det><ind><sg>$ ^beautiful<adj>$ ^country<n><sg>$^.<sent>$^.<sent>$

==For '''Item 2: Noun-adjective order in noun phraseology: adjectives now come before the noun in translations when necessary:'''==

Applying rule 3 (line 58): ^sardu<n><m><sg>/Sardinian<n><sg>$

Applying rule 4 (line 60): ^Su<det><def><m><sg>/The<det><def><m><sg>$ ^Default<NP><PD><ND>{^sardu<n><m><sg>/Sardinian<n><sg>$}$

Applying rule 6 (line 63): ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$

Applying rule 11 (line 69): ^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$

Applying rule 12 (line 71): ^Default<DP><PD><ND>{^Su<det><def><m><sg>/The<det><def><m><sg>$ ^Default<NP><PD><ND>{^sardu<n><m><sg>/Sardinian<n><sg>$}$}$ ^be<VP><p3><sg>{^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$}$

Applying rule 6 (line 63): ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$

Applying rule 11 (line 69): ^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$

Applying rule 13 (line 72): ^Default<NP><PD><ND>{^sardu<n><m><sg>/Sardinian<n><sg>$}$ ^be<VP><p3><sg>{^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$}$

Applying rule 3 (line 58): ^limba<n><f><sg>/language<n><sg>$

Applying rule 4 (line 60): ^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$}$

Applying rule 9 (line 67): ^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$}$}$

Applying rule 12 (line 71): ^Default<DP><PD><ND>{^Su<det><def><m><sg>/The<det><def><m><sg>$ ^Default<NP><PD><ND>{^sardu<n><m><sg>/Sardinian<n><sg>$}$}$ ^be<VP><p3><sg>{^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$}$}$}$

Applying rule 3 (line 58): ^limba<n><f><sg>/language<n><sg>$

Applying rule 4 (line 60): ^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$}$

Applying rule 9 (line 67): ^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$}$}$

Applying rule 13 (line 72): ^Default<NP><PD><ND>{^sardu<n><m><sg>/Sardinian<n><sg>$}$ ^be<VP><p3><sg>{^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$}$}$}$

Applying rule 1 (line 56): ^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$

Applying rule 4 (line 60): ^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$}$

Applying rule 9 (line 67): ^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$}$}$

Applying rule 12 (line 71): ^Default<DP><PD><ND>{^Su<det><def><m><sg>/The<det><def><m><sg>$ ^Default<NP><PD><ND>{^sardu<n><m><sg>/Sardinian<n><sg>$}$}$ ^be<VP><p3><sg>{^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$}$}$}$

Applying rule 1 (line 56): ^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$

Applying rule 4 (line 60): ^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$}$

Applying rule 9 (line 67): ^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$}$}$

Applying rule 13 (line 72): ^Default<NP><PD><ND>{^sardu<n><m><sg>/Sardinian<n><sg>$}$ ^be<VP><p3><sg>{^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$}$}$}$

Applying output rule 11 (line 71): Be<#S><p3><sg> -> ^Default<DP><PD><ND>{^Su<det><def><m><sg>/The<det><def><m><sg>$ ^Default<NP><PD><ND>{^sardu<n><m><sg>/Sardinian<n><sg>$}$}$ ^be<VP><p3><sg>{^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$}$}$}$

Applying output rule 3 (line 60): Default<DP><p3><sg> -> ^Su<det><def><m><sg>/The<det><def><m><sg>$ ^Default<NP><PD><ND>{^sardu<n><m><sg>/Sardinian<n><sg>$}$

No rule specified: ^The<det><def><sg>$

Applying output rule 2 (line 58): Default<NP><p3><sg> -> ^sardu<n><m><sg>/Sardinian<n><sg>$

No rule specified: ^Sardinian<n><sg>$

Applying output rule 8 (line 67): be<VP><p3><sg> -> ^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$}$}$

Applying output rule 5 (line 63): be<vP><p3><sg> -> ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$

No rule specified: ^be<vbser><pres><p3><sg>$

Applying output rule 3 (line 60): default<DP><p3><sg> -> ^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$}$

No rule specified: ^a<det><ind><sg>$

Applying output rule 0 (line 56): default<NP><p3><sg> -> ^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$

No rule specified: ^ancient<adj>$

No rule specified: ^language<n><sg>$

No rule specified: ^.<sent>/.<sent>$

No rule specified: ^.<sent>/.<sent>$
^The<det><def><sg>$ ^Sardinian<n><sg>$ ^be<vbser><pres><p3><sg>$ ^a<det><ind><sg>$ ^ancient<adj>$ ^language<n><sg>$^.<sent>$^.<sent>$

==For '''Item 4: For most uses/conjugations of verbs in Sardinian, the verb stands on its own without a personal pronoun, while in English personal pronouns always precede any conjugated verbs. In other words, the tags of "appo" (I have) determine a new word "I" which precedes "have" in the English translation.'''==

Applying rule 7 (line 64): ^Àere<vbhaver><pri><p1><sg>/Have<vbhaver><pri><p1><sg>$
Applying rule 11 (line 69): ^Have<vP><p1><sg>{^Àere<vbhaver><pri><p1><sg>/Have<vbhaver><pri><p1><sg>$}$
Applying rule 15 (line 74): ^Have<VP><p1><sg>{^Have<vP><p1><sg>{^Àere<vbhaver><pri><p1><sg>/Have<vbhaver><pri><p1><sg>$}$}$
Applying rule 8 (line 65): ^pèrdere<vblex><pp><m><sg>/lose<vblex><pp><m><sg>$
Applying rule 10 (line 68): ^Have<vP><p1><sg>{^Àere<vbhaver><pri><p1><sg>/Have<vbhaver><pri><p1><sg>$}$ ^lose<vP><PD><sg>{^pèrdere<vblex><pp><m><sg>/lose<vblex><pp><m><sg>$}$
Applying rule 15 (line 74): ^Have<VP><p1><sg>{^Have<vP><p1><sg>{^Àere<vbhaver><pri><p1><sg>/Have<vbhaver><pri><p1><sg>$}$ ^lose<vP><PD><sg>{^pèrdere<vblex><pp><m><sg>/lose<vblex><pp><m><sg>$}$}$
Applying output rule 14 (line 74): Have<#S><p1><sg> -> ^Have<VP><p1><sg>{^Have<vP><p1><sg>{^Àere<vbhaver><pri><p1><sg>/Have<vbhaver><pri><p1><sg>$}$ ^lose<vP><PD><sg>{^pèrdere<vblex><pp><m><sg>/lose<vblex><pp><m><sg>$}$}$
No rule specified: ^prpers<prn><subj><p1><mf><sg>$
Applying output rule 9 (line 68): Have<VP><p1><sg> -> ^Have<vP><p1><sg>{^Àere<vbhaver><pri><p1><sg>/Have<vbhaver><pri><p1><sg>$}$ ^lose<vP><PD><sg>{^pèrdere<vblex><pp><m><sg>/lose<vblex><pp><m><sg>$}$
Applying output rule 6 (line 64): Have<vP><p1><sg> -> ^Àere<vbhaver><pri><p1><sg>/Have<vbhaver><pri><p1><sg>$
No rule specified: ^Have<vbhaver><pres><p1><sg>$=
Applying output rule 7 (line 65): lose<vP><p3><sg> -> ^pèrdere<vblex><pp><m><sg>/lose<vblex><pp><m><sg>$
No rule specified: ^lose<vblex><p3><sg>$
No rule specified: ^duos<num><m><sp>/two<num><m><sp>$
No rule specified: ^de<pr>/of<pr>$
Applying rule 3 (line 58): ^libru<n><m><pl>/book<n><pl>$
Applying rule 4 (line 60): ^su<det><def><m><pl>/the<det><def><m><pl>$ ^default<NP><PD><ND>{^libru<n><m><pl>/book<n><pl>$}$
Applying rule 1 (line 56): ^libru<n><m><pl>/book<n><pl>$ ^meu<adj><pos><m><pl>/my<det><pos><m><pl>$
Applying rule 4 (line 60): ^su<det><def><m><pl>/the<det><def><m><pl>$ ^default<NP><PD><ND>{^libru<n><m><pl>/book<n><pl>$ ^meu<adj><pos><m><pl>/my<det><pos><m><pl>$}$
Applying output rule 3 (line 60): default<DP><PD><ND> -> ^su<det><def><m><pl>/the<det><def><m><pl>$ ^default<NP><PD><ND>{^libru<n><m><pl>/book<n><pl>$ ^meu<adj><pos><m><pl>/my<det><pos><m><pl>$}$
No rule specified: ^the<det><def><pl>$
Applying output rule 0 (line 56): default<NP><p3><sg> -> ^libru<n><m><pl>/book<n><pl>$ ^meu<adj><pos><m><pl>/my<det><pos><m><pl>$
No rule specified: ^my<det>$

[[Category:Sp23_StructuralTransfer]],[[Category:Sardinian]],[[Category:English]]
No rule specified: ^book<n><pl>$
No rule specified: ^.<sent>/.<sent>$
No rule specified: ^.<sent>/.<sent>$
^prpers<prn><subj><p1><mf><sg>$ ^Have<vbhaver><pres><p1><sg>$ ^lose<vblex><p3><sg>$ ^two<num><m><sp>$ ^of<pr>$ ^the<det><def><pl>$ ^my<det>$ ^book<n><pl>$^.<sent>$^.<sent>$

Sardinian and English/Structural transfer

2023-05-04T15:40:37Z

Rorlija1: /* Item 1: Determiners before nouns in Sardinian are omitted in English translations that do not include determiners before nouns */

Sardinian and English/Structural transfer output

2023-05-04T15:39:54Z

Rorlija1: /* For Item 1: Determiners before nouns in Sardinian are omitted in English translations that do not include determiners before nouns */

Given that the output of the srd-eng-transfer is quite lengthy in some instances, I've opted to create this page to reduce clutter on the main structural transfer page.

==For '''Item 1: Determiners before nouns in Sardinian are omitted in English translations that do not include determiners before nouns'''==

Applying rule 5 (line 61): ^Su<det><def><f><sg>/The<det><def><f><sg>$ ^Frantza<np><top><f><sg>/France<np><top><f><sg>$

Applying rule 6 (line 63): ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$

Applying rule 11 (line 69): ^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$

Applying rule 12 (line 71): ^Default<DP><PD><ND>{^Su<det><def><f><sg>/The<det><def><f><sg>$ ^Frantza<np><top><f><sg>/France<np><top><f><sg>$}$ ^be<VP><p3><sg>{^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$}$

Applying rule 3 (line 58): ^paisu<n><m><sg>/country<n><sg>$

Applying rule 4 (line 60): ^unu<det><ind><m><sg>/a<det><ind><m><sg>$ ^default<NP><PD><ND>{^paisu<n><m><sg>/country<n><sg>$}$

Applying rule 9 (line 67): ^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><m><sg>/a<det><ind><m><sg>$ ^default<NP><PD><ND>{^paisu<n><m><sg>/country<n><sg>$}$}$

Applying rule 12 (line 71): ^Default<DP><PD><ND>{^Su<det><def><f><sg>/The<det><def><f><sg>$ ^Frantza<np><top><f><sg>/France<np><top><f><sg>$}$ ^be<VP><p3><sg>{^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><m><sg>/a<det><ind><m><sg>$ ^default<NP><PD><ND>{^paisu<n><m><sg>/country<n><sg>$}$}$}$

Applying rule 1 (line 56): ^paisu<n><m><sg>/country<n><sg>$ ^bellu<adj><m><sg>/beautiful<adj><m><sg>$

Applying rule 4 (line 60): ^unu<det><ind><m><sg>/a<det><ind><m><sg>$ ^default<NP><PD><ND>{^paisu<n><m><sg>/country<n><sg>$ ^bellu<adj><m><sg>/beautiful<adj><m><sg>$}$

Applying rule 9 (line 67): ^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><m><sg>/a<det><ind><m><sg>$ ^default<NP><PD><ND>{^paisu<n><m><sg>/country<n><sg>$ ^bellu<adj><m><sg>/beautiful<adj><m><sg>$}$}$

Applying rule 12 (line 71): ^Default<DP><PD><ND>{^Su<det><def><f><sg>/The<det><def><f><sg>$ ^Frantza<np><top><f><sg>/France<np><top><f><sg>$}$ ^be<VP><p3><sg>{^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><m><sg>/a<det><ind><m><sg>$ ^default<NP><PD><ND>{^paisu<n><m><sg>/country<n><sg>$ ^bellu<adj><m><sg>/beautiful<adj><m><sg>$}$}$}$

Applying output rule 11 (line 71): Be<#S><p3><sg> -> ^Default<DP><PD><ND>{^Su<det><def><f><sg>/The<det><def><f><sg>$ ^Frantza<np><top><f><sg>/France<np><top><f><sg>$}$ ^be<VP><p3><sg>{^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><m><sg>/a<det><ind><m><sg>$ ^default<NP><PD><ND>{^paisu<n><m><sg>/country<n><sg>$ ^bellu<adj><m><sg>/beautiful<adj><m><sg>$}$}$}$

Applying output rule 4 (line 61): Default<DP><p3><sg> -> ^Su<det><def><f><sg>/The<det><def><f><sg>$ ^Frantza<np><top><f><sg>/France<np><top><f><sg>$

No rule specified: ^France<np><top><sg>$

Applying output rule 8 (line 67): be<VP><p3><sg> -> ^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><m><sg>/a<det><ind><m><sg>$ ^default<NP><PD><ND>{^paisu<n><m><sg>/country<n><sg>$ ^bellu<adj><m><sg>/beautiful<adj><m><sg>$}$}$

Applying output rule 5 (line 63): be<vP><p3><sg> -> ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$

No rule specified: ^be<vbser><pres><p3><sg>$

Applying output rule 3 (line 60): default<DP><p3><sg> -> ^unu<det><ind><m><sg>/a<det><ind><m><sg>$ ^default<NP><PD><ND>{^paisu<n><m><sg>/country<n><sg>$ ^bellu<adj><m><sg>/beautiful<adj><m><sg>$}$

No rule specified: ^a<det><ind><sg>$

Applying output rule 0 (line 56): default<NP><p3><sg> -> ^paisu<n><m><sg>/country<n><sg>$ ^bellu<adj><m><sg>/beautiful<adj><m><sg>$

No rule specified: ^beautiful<adj>$

No rule specified: ^country<n><sg>$

No rule specified: ^.<sent>/.<sent>$

No rule specified: ^.<sent>/.<sent>$
^France<np><top><sg>$ ^be<vbser><pres><p3><sg>$ ^a<det><ind><sg>$ ^beautiful<adj>$ ^country<n><sg>$^.<sent>$^.<sent>$

==For '''Item 2: Noun-adjective order in noun phraseology: adjectives now come before the noun in translations when necessary:'''==

Applying rule 3 (line 58): ^sardu<n><m><sg>/Sardinian<n><sg>$

Applying rule 4 (line 60): ^Su<det><def><m><sg>/The<det><def><m><sg>$ ^Default<NP><PD><ND>{^sardu<n><m><sg>/Sardinian<n><sg>$}$

Applying rule 6 (line 63): ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$

Applying rule 11 (line 69): ^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$

Applying rule 12 (line 71): ^Default<DP><PD><ND>{^Su<det><def><m><sg>/The<det><def><m><sg>$ ^Default<NP><PD><ND>{^sardu<n><m><sg>/Sardinian<n><sg>$}$}$ ^be<VP><p3><sg>{^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$}$

Applying rule 6 (line 63): ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$

Applying rule 11 (line 69): ^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$

Applying rule 13 (line 72): ^Default<NP><PD><ND>{^sardu<n><m><sg>/Sardinian<n><sg>$}$ ^be<VP><p3><sg>{^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$}$

Applying rule 3 (line 58): ^limba<n><f><sg>/language<n><sg>$

Applying rule 4 (line 60): ^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$}$

Applying rule 9 (line 67): ^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$}$}$

Applying rule 12 (line 71): ^Default<DP><PD><ND>{^Su<det><def><m><sg>/The<det><def><m><sg>$ ^Default<NP><PD><ND>{^sardu<n><m><sg>/Sardinian<n><sg>$}$}$ ^be<VP><p3><sg>{^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$}$}$}$

Applying rule 3 (line 58): ^limba<n><f><sg>/language<n><sg>$

Applying rule 4 (line 60): ^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$}$

Applying rule 9 (line 67): ^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$}$}$

Applying rule 13 (line 72): ^Default<NP><PD><ND>{^sardu<n><m><sg>/Sardinian<n><sg>$}$ ^be<VP><p3><sg>{^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$}$}$}$

Applying rule 1 (line 56): ^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$

Applying rule 4 (line 60): ^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$}$

Applying rule 9 (line 67): ^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$}$}$

Applying rule 12 (line 71): ^Default<DP><PD><ND>{^Su<det><def><m><sg>/The<det><def><m><sg>$ ^Default<NP><PD><ND>{^sardu<n><m><sg>/Sardinian<n><sg>$}$}$ ^be<VP><p3><sg>{^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$}$}$}$

Applying rule 1 (line 56): ^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$

Applying rule 4 (line 60): ^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$}$

Applying rule 9 (line 67): ^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$}$}$

Applying rule 13 (line 72): ^Default<NP><PD><ND>{^sardu<n><m><sg>/Sardinian<n><sg>$}$ ^be<VP><p3><sg>{^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$}$}$}$

Applying output rule 11 (line 71): Be<#S><p3><sg> -> ^Default<DP><PD><ND>{^Su<det><def><m><sg>/The<det><def><m><sg>$ ^Default<NP><PD><ND>{^sardu<n><m><sg>/Sardinian<n><sg>$}$}$ ^be<VP><p3><sg>{^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$}$}$}$

Applying output rule 3 (line 60): Default<DP><p3><sg> -> ^Su<det><def><m><sg>/The<det><def><m><sg>$ ^Default<NP><PD><ND>{^sardu<n><m><sg>/Sardinian<n><sg>$}$

No rule specified: ^The<det><def><sg>$

Applying output rule 2 (line 58): Default<NP><p3><sg> -> ^sardu<n><m><sg>/Sardinian<n><sg>$

No rule specified: ^Sardinian<n><sg>$

Applying output rule 8 (line 67): be<VP><p3><sg> -> ^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$}$}$

Applying output rule 5 (line 63): be<vP><p3><sg> -> ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$

No rule specified: ^be<vbser><pres><p3><sg>$

Applying output rule 3 (line 60): default<DP><p3><sg> -> ^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$}$

No rule specified: ^a<det><ind><sg>$

Applying output rule 0 (line 56): default<NP><p3><sg> -> ^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$

No rule specified: ^ancient<adj>$

No rule specified: ^language<n><sg>$

No rule specified: ^.<sent>/.<sent>$

No rule specified: ^.<sent>/.<sent>$
^The<det><def><sg>$ ^Sardinian<n><sg>$ ^be<vbser><pres><p3><sg>$ ^a<det><ind><sg>$ ^ancient<adj>$ ^language<n><sg>$^.<sent>$^.<sent>$

==For '''Item 4: For most uses/conjugations of verbs in Sardinian, the verb stands on its own without a personal pronoun, while in English personal pronouns always precede any conjugated verbs. In other words, the tags of "appo" (I have) determine a new word "I" which precedes "have" in the English translation.'''==

Applying rule 7 (line 64): ^Àere<vbhaver><pri><p1><sg>/Have<vbhaver><pri><p1><sg>$
Applying rule 11 (line 69): ^Have<vP><p1><sg>{^Àere<vbhaver><pri><p1><sg>/Have<vbhaver><pri><p1><sg>$}$
Applying rule 15 (line 74): ^Have<VP><p1><sg>{^Have<vP><p1><sg>{^Àere<vbhaver><pri><p1><sg>/Have<vbhaver><pri><p1><sg>$}$}$
Applying rule 8 (line 65): ^pèrdere<vblex><pp><m><sg>/lose<vblex><pp><m><sg>$
Applying rule 10 (line 68): ^Have<vP><p1><sg>{^Àere<vbhaver><pri><p1><sg>/Have<vbhaver><pri><p1><sg>$}$ ^lose<vP><PD><sg>{^pèrdere<vblex><pp><m><sg>/lose<vblex><pp><m><sg>$}$
Applying rule 15 (line 74): ^Have<VP><p1><sg>{^Have<vP><p1><sg>{^Àere<vbhaver><pri><p1><sg>/Have<vbhaver><pri><p1><sg>$}$ ^lose<vP><PD><sg>{^pèrdere<vblex><pp><m><sg>/lose<vblex><pp><m><sg>$}$}$
Applying output rule 14 (line 74): Have<#S><p1><sg> -> ^Have<VP><p1><sg>{^Have<vP><p1><sg>{^Àere<vbhaver><pri><p1><sg>/Have<vbhaver><pri><p1><sg>$}$ ^lose<vP><PD><sg>{^pèrdere<vblex><pp><m><sg>/lose<vblex><pp><m><sg>$}$}$
No rule specified: ^prpers<prn><subj><p1><mf><sg>$
Applying output rule 9 (line 68): Have<VP><p1><sg> -> ^Have<vP><p1><sg>{^Àere<vbhaver><pri><p1><sg>/Have<vbhaver><pri><p1><sg>$}$ ^lose<vP><PD><sg>{^pèrdere<vblex><pp><m><sg>/lose<vblex><pp><m><sg>$}$
Applying output rule 6 (line 64): Have<vP><p1><sg> -> ^Àere<vbhaver><pri><p1><sg>/Have<vbhaver><pri><p1><sg>$
No rule specified: ^Have<vbhaver><pres><p1><sg>$=
Applying output rule 7 (line 65): lose<vP><p3><sg> -> ^pèrdere<vblex><pp><m><sg>/lose<vblex><pp><m><sg>$
No rule specified: ^lose<vblex><p3><sg>$
No rule specified: ^duos<num><m><sp>/two<num><m><sp>$
No rule specified: ^de<pr>/of<pr>$
Applying rule 3 (line 58): ^libru<n><m><pl>/book<n><pl>$
Applying rule 4 (line 60): ^su<det><def><m><pl>/the<det><def><m><pl>$ ^default<NP><PD><ND>{^libru<n><m><pl>/book<n><pl>$}$
Applying rule 1 (line 56): ^libru<n><m><pl>/book<n><pl>$ ^meu<adj><pos><m><pl>/my<det><pos><m><pl>$
Applying rule 4 (line 60): ^su<det><def><m><pl>/the<det><def><m><pl>$ ^default<NP><PD><ND>{^libru<n><m><pl>/book<n><pl>$ ^meu<adj><pos><m><pl>/my<det><pos><m><pl>$}$
Applying output rule 3 (line 60): default<DP><PD><ND> -> ^su<det><def><m><pl>/the<det><def><m><pl>$ ^default<NP><PD><ND>{^libru<n><m><pl>/book<n><pl>$ ^meu<adj><pos><m><pl>/my<det><pos><m><pl>$}$
No rule specified: ^the<det><def><pl>$
Applying output rule 0 (line 56): default<NP><p3><sg> -> ^libru<n><m><pl>/book<n><pl>$ ^meu<adj><pos><m><pl>/my<det><pos><m><pl>$
No rule specified: ^my<det>$
No rule specified: ^book<n><pl>$
No rule specified: ^.<sent>/.<sent>$
No rule specified: ^.<sent>/.<sent>$
^prpers<prn><subj><p1><mf><sg>$ ^Have<vbhaver><pres><p1><sg>$ ^lose<vblex><p3><sg>$ ^two<num><m><sp>$ ^of<pr>$ ^the<det><def><pl>$ ^my<det>$ ^book<n><pl>$^.<sent>$^.<sent>$

Sardinian and English/Structural transfer output

2023-05-04T15:39:38Z

Rorlija1:

Given that the output of the srd-eng-transfer is quite lengthy in some instances, I've opted to create this page to reduce clutter on the main structural transfer page.

==For '''Item 1: Determiners before nouns in Sardinian are omitted in English translations that do not include determiners before nouns'''==

Applying rule 5 (line 61): ^Su<det><def><f><sg>/The<det><def><f><sg>$ ^Frantza<np><top><f><sg>/France<np><top><f><sg>$

Applying rule 6 (line 63): ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$

Applying rule 11 (line 69): ^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$

Applying rule 12 (line 71): ^Default<DP><PD><ND>{^Su<det><def><f><sg>/The<det><def><f><sg>$ ^Frantza<np><top><f><sg>/France<np><top><f><sg>$}$ ^be<VP><p3><sg>{^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$}$

Applying rule 3 (line 58): ^paisu<n><m><sg>/country<n><sg>$

Applying rule 4 (line 60): ^unu<det><ind><m><sg>/a<det><ind><m><sg>$ ^default<NP><PD><ND>{^paisu<n><m><sg>/country<n><sg>$}$

Applying rule 9 (line 67): ^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><m><sg>/a<det><ind><m><sg>$ ^default<NP><PD><ND>{^paisu<n><m><sg>/country<n><sg>$}$}$

Applying rule 12 (line 71): ^Default<DP><PD><ND>{^Su<det><def><f><sg>/The<det><def><f><sg>$ ^Frantza<np><top><f><sg>/France<np><top><f><sg>$}$ ^be<VP><p3><sg>{^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><m><sg>/a<det><ind><m><sg>$ ^default<NP><PD><ND>{^paisu<n><m><sg>/country<n><sg>$}$}$}$

Applying rule 1 (line 56): ^paisu<n><m><sg>/country<n><sg>$ ^bellu<adj><m><sg>/beautiful<adj><m><sg>$

Applying rule 4 (line 60): ^unu<det><ind><m><sg>/a<det><ind><m><sg>$ ^default<NP><PD><ND>{^paisu<n><m><sg>/country<n><sg>$ ^bellu<adj><m><sg>/beautiful<adj><m><sg>$}$

Applying rule 9 (line 67): ^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><m><sg>/a<det><ind><m><sg>$ ^default<NP><PD><ND>{^paisu<n><m><sg>/country<n><sg>$ ^bellu<adj><m><sg>/beautiful<adj><m><sg>$}$}$

Applying rule 12 (line 71): ^Default<DP><PD><ND>{^Su<det><def><f><sg>/The<det><def><f><sg>$ ^Frantza<np><top><f><sg>/France<np><top><f><sg>$}$ ^be<VP><p3><sg>{^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><m><sg>/a<det><ind><m><sg>$ ^default<NP><PD><ND>{^paisu<n><m><sg>/country<n><sg>$ ^bellu<adj><m><sg>/beautiful<adj><m><sg>$}$}$}$

Applying output rule 11 (line 71): Be<S><p3><sg> -> ^Default<DP><PD><ND>{^Su<det><def><f><sg>/The<det><def><f><sg>$ ^Frantza<np><top><f><sg>/France<np><top><f><sg>$}$ ^be<VP><p3><sg>{^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><m><sg>/a<det><ind><m><sg>$ ^default<NP><PD><ND>{^paisu<n><m><sg>/country<n><sg>$ ^bellu<adj><m><sg>/beautiful<adj><m><sg>$}$}$}$

Applying output rule 4 (line 61): Default<DP><p3><sg> -> ^Su<det><def><f><sg>/The<det><def><f><sg>$ ^Frantza<np><top><f><sg>/France<np><top><f><sg>$

No rule specified: ^France<np><top><sg>$

Applying output rule 8 (line 67): be<VP><p3><sg> -> ^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><m><sg>/a<det><ind><m><sg>$ ^default<NP><PD><ND>{^paisu<n><m><sg>/country<n><sg>$ ^bellu<adj><m><sg>/beautiful<adj><m><sg>$}$}$

Applying output rule 5 (line 63): be<vP><p3><sg> -> ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$

No rule specified: ^be<vbser><pres><p3><sg>$

Applying output rule 3 (line 60): default<DP><p3><sg> -> ^unu<det><ind><m><sg>/a<det><ind><m><sg>$ ^default<NP><PD><ND>{^paisu<n><m><sg>/country<n><sg>$ ^bellu<adj><m><sg>/beautiful<adj><m><sg>$}$

No rule specified: ^a<det><ind><sg>$

Applying output rule 0 (line 56): default<NP><p3><sg> -> ^paisu<n><m><sg>/country<n><sg>$ ^bellu<adj><m><sg>/beautiful<adj><m><sg>$

No rule specified: ^beautiful<adj>$

No rule specified: ^country<n><sg>$

No rule specified: ^.<sent>/.<sent>$

No rule specified: ^.<sent>/.<sent>$
^France<np><top><sg>$ ^be<vbser><pres><p3><sg>$ ^a<det><ind><sg>$ ^beautiful<adj>$ ^country<n><sg>$^.<sent>$^.<sent>$

==For '''Item 2: Noun-adjective order in noun phraseology: adjectives now come before the noun in translations when necessary:'''==

Applying rule 3 (line 58): ^sardu<n><m><sg>/Sardinian<n><sg>$

Applying rule 4 (line 60): ^Su<det><def><m><sg>/The<det><def><m><sg>$ ^Default<NP><PD><ND>{^sardu<n><m><sg>/Sardinian<n><sg>$}$

Applying rule 6 (line 63): ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$

Applying rule 11 (line 69): ^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$

Applying rule 12 (line 71): ^Default<DP><PD><ND>{^Su<det><def><m><sg>/The<det><def><m><sg>$ ^Default<NP><PD><ND>{^sardu<n><m><sg>/Sardinian<n><sg>$}$}$ ^be<VP><p3><sg>{^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$}$

Applying rule 6 (line 63): ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$

Applying rule 11 (line 69): ^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$

Applying rule 13 (line 72): ^Default<NP><PD><ND>{^sardu<n><m><sg>/Sardinian<n><sg>$}$ ^be<VP><p3><sg>{^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$}$

Applying rule 3 (line 58): ^limba<n><f><sg>/language<n><sg>$

Applying rule 4 (line 60): ^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$}$

Applying rule 9 (line 67): ^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$}$}$

Applying rule 12 (line 71): ^Default<DP><PD><ND>{^Su<det><def><m><sg>/The<det><def><m><sg>$ ^Default<NP><PD><ND>{^sardu<n><m><sg>/Sardinian<n><sg>$}$}$ ^be<VP><p3><sg>{^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$}$}$}$

Applying rule 3 (line 58): ^limba<n><f><sg>/language<n><sg>$

Applying rule 4 (line 60): ^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$}$

Applying rule 9 (line 67): ^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$}$}$

Applying rule 13 (line 72): ^Default<NP><PD><ND>{^sardu<n><m><sg>/Sardinian<n><sg>$}$ ^be<VP><p3><sg>{^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$}$}$}$

Applying rule 1 (line 56): ^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$

Applying rule 4 (line 60): ^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$}$

Applying rule 9 (line 67): ^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$}$}$

Applying rule 12 (line 71): ^Default<DP><PD><ND>{^Su<det><def><m><sg>/The<det><def><m><sg>$ ^Default<NP><PD><ND>{^sardu<n><m><sg>/Sardinian<n><sg>$}$}$ ^be<VP><p3><sg>{^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$}$}$}$

Applying rule 1 (line 56): ^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$

Applying rule 4 (line 60): ^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$}$

Applying rule 9 (line 67): ^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$}$}$

Applying rule 13 (line 72): ^Default<NP><PD><ND>{^sardu<n><m><sg>/Sardinian<n><sg>$}$ ^be<VP><p3><sg>{^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$}$}$}$

Applying output rule 11 (line 71): Be<#S><p3><sg> -> ^Default<DP><PD><ND>{^Su<det><def><m><sg>/The<det><def><m><sg>$ ^Default<NP><PD><ND>{^sardu<n><m><sg>/Sardinian<n><sg>$}$}$ ^be<VP><p3><sg>{^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$}$}$}$

Applying output rule 3 (line 60): Default<DP><p3><sg> -> ^Su<det><def><m><sg>/The<det><def><m><sg>$ ^Default<NP><PD><ND>{^sardu<n><m><sg>/Sardinian<n><sg>$}$

No rule specified: ^The<det><def><sg>$

Applying output rule 2 (line 58): Default<NP><p3><sg> -> ^sardu<n><m><sg>/Sardinian<n><sg>$

No rule specified: ^Sardinian<n><sg>$

Applying output rule 8 (line 67): be<VP><p3><sg> -> ^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$}$}$

Applying output rule 5 (line 63): be<vP><p3><sg> -> ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$

No rule specified: ^be<vbser><pres><p3><sg>$

Applying output rule 3 (line 60): default<DP><p3><sg> -> ^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$}$

No rule specified: ^a<det><ind><sg>$

Applying output rule 0 (line 56): default<NP><p3><sg> -> ^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$

No rule specified: ^ancient<adj>$

No rule specified: ^language<n><sg>$

No rule specified: ^.<sent>/.<sent>$

No rule specified: ^.<sent>/.<sent>$
^The<det><def><sg>$ ^Sardinian<n><sg>$ ^be<vbser><pres><p3><sg>$ ^a<det><ind><sg>$ ^ancient<adj>$ ^language<n><sg>$^.<sent>$^.<sent>$

==For '''Item 4: For most uses/conjugations of verbs in Sardinian, the verb stands on its own without a personal pronoun, while in English personal pronouns always precede any conjugated verbs. In other words, the tags of "appo" (I have) determine a new word "I" which precedes "have" in the English translation.'''==

Applying rule 7 (line 64): ^Àere<vbhaver><pri><p1><sg>/Have<vbhaver><pri><p1><sg>$
Applying rule 11 (line 69): ^Have<vP><p1><sg>{^Àere<vbhaver><pri><p1><sg>/Have<vbhaver><pri><p1><sg>$}$
Applying rule 15 (line 74): ^Have<VP><p1><sg>{^Have<vP><p1><sg>{^Àere<vbhaver><pri><p1><sg>/Have<vbhaver><pri><p1><sg>$}$}$
Applying rule 8 (line 65): ^pèrdere<vblex><pp><m><sg>/lose<vblex><pp><m><sg>$
Applying rule 10 (line 68): ^Have<vP><p1><sg>{^Àere<vbhaver><pri><p1><sg>/Have<vbhaver><pri><p1><sg>$}$ ^lose<vP><PD><sg>{^pèrdere<vblex><pp><m><sg>/lose<vblex><pp><m><sg>$}$
Applying rule 15 (line 74): ^Have<VP><p1><sg>{^Have<vP><p1><sg>{^Àere<vbhaver><pri><p1><sg>/Have<vbhaver><pri><p1><sg>$}$ ^lose<vP><PD><sg>{^pèrdere<vblex><pp><m><sg>/lose<vblex><pp><m><sg>$}$}$
Applying output rule 14 (line 74): Have<#S><p1><sg> -> ^Have<VP><p1><sg>{^Have<vP><p1><sg>{^Àere<vbhaver><pri><p1><sg>/Have<vbhaver><pri><p1><sg>$}$ ^lose<vP><PD><sg>{^pèrdere<vblex><pp><m><sg>/lose<vblex><pp><m><sg>$}$}$
No rule specified: ^prpers<prn><subj><p1><mf><sg>$
Applying output rule 9 (line 68): Have<VP><p1><sg> -> ^Have<vP><p1><sg>{^Àere<vbhaver><pri><p1><sg>/Have<vbhaver><pri><p1><sg>$}$ ^lose<vP><PD><sg>{^pèrdere<vblex><pp><m><sg>/lose<vblex><pp><m><sg>$}$
Applying output rule 6 (line 64): Have<vP><p1><sg> -> ^Àere<vbhaver><pri><p1><sg>/Have<vbhaver><pri><p1><sg>$
No rule specified: ^Have<vbhaver><pres><p1><sg>$=
Applying output rule 7 (line 65): lose<vP><p3><sg> -> ^pèrdere<vblex><pp><m><sg>/lose<vblex><pp><m><sg>$
No rule specified: ^lose<vblex><p3><sg>$
No rule specified: ^duos<num><m><sp>/two<num><m><sp>$
No rule specified: ^de<pr>/of<pr>$
Applying rule 3 (line 58): ^libru<n><m><pl>/book<n><pl>$
Applying rule 4 (line 60): ^su<det><def><m><pl>/the<det><def><m><pl>$ ^default<NP><PD><ND>{^libru<n><m><pl>/book<n><pl>$}$
Applying rule 1 (line 56): ^libru<n><m><pl>/book<n><pl>$ ^meu<adj><pos><m><pl>/my<det><pos><m><pl>$
Applying rule 4 (line 60): ^su<det><def><m><pl>/the<det><def><m><pl>$ ^default<NP><PD><ND>{^libru<n><m><pl>/book<n><pl>$ ^meu<adj><pos><m><pl>/my<det><pos><m><pl>$}$
Applying output rule 3 (line 60): default<DP><PD><ND> -> ^su<det><def><m><pl>/the<det><def><m><pl>$ ^default<NP><PD><ND>{^libru<n><m><pl>/book<n><pl>$ ^meu<adj><pos><m><pl>/my<det><pos><m><pl>$}$
No rule specified: ^the<det><def><pl>$
Applying output rule 0 (line 56): default<NP><p3><sg> -> ^libru<n><m><pl>/book<n><pl>$ ^meu<adj><pos><m><pl>/my<det><pos><m><pl>$
No rule specified: ^my<det>$
No rule specified: ^book<n><pl>$
No rule specified: ^.<sent>/.<sent>$
No rule specified: ^.<sent>/.<sent>$
^prpers<prn><subj><p1><mf><sg>$ ^Have<vbhaver><pres><p1><sg>$ ^lose<vblex><p3><sg>$ ^two<num><m><sp>$ ^of<pr>$ ^the<det><def><pl>$ ^my<det>$ ^book<n><pl>$^.<sent>$^.<sent>$

Sardinian and English/Structural transfer

2023-05-04T15:37:44Z

Rorlija1: /* Item 4: For most uses/conjugations of verbs in Sardinian, the verb stands on its own without a personal pronoun, while in English personal pronouns always precede any conjugated verbs. In other words, the tags of "appo" (I have) determine a new word...

Sardinian and English/Structural transfer output

2023-05-04T15:36:58Z

Rorlija1:

Given that the output of the srd-eng-transfer is quite lengthy in some instances, I've opted to create this page to reduce clutter on the main structural transfer page.

==For '''Item 2: Noun-adjective order in noun phraseology: adjectives now come before the noun in translations when necessary:'''==

Applying rule 3 (line 58): ^sardu<n><m><sg>/Sardinian<n><sg>$

Applying rule 4 (line 60): ^Su<det><def><m><sg>/The<det><def><m><sg>$ ^Default<NP><PD><ND>{^sardu<n><m><sg>/Sardinian<n><sg>$}$

Applying rule 6 (line 63): ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$

Applying rule 11 (line 69): ^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$

Applying rule 12 (line 71): ^Default<DP><PD><ND>{^Su<det><def><m><sg>/The<det><def><m><sg>$ ^Default<NP><PD><ND>{^sardu<n><m><sg>/Sardinian<n><sg>$}$}$ ^be<VP><p3><sg>{^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$}$

Applying rule 6 (line 63): ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$

Applying rule 11 (line 69): ^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$

Applying rule 13 (line 72): ^Default<NP><PD><ND>{^sardu<n><m><sg>/Sardinian<n><sg>$}$ ^be<VP><p3><sg>{^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$}$

Applying rule 3 (line 58): ^limba<n><f><sg>/language<n><sg>$

Applying rule 4 (line 60): ^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$}$

Applying rule 9 (line 67): ^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$}$}$

Applying rule 12 (line 71): ^Default<DP><PD><ND>{^Su<det><def><m><sg>/The<det><def><m><sg>$ ^Default<NP><PD><ND>{^sardu<n><m><sg>/Sardinian<n><sg>$}$}$ ^be<VP><p3><sg>{^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$}$}$}$

Applying rule 3 (line 58): ^limba<n><f><sg>/language<n><sg>$

Applying rule 4 (line 60): ^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$}$

Applying rule 9 (line 67): ^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$}$}$

Applying rule 13 (line 72): ^Default<NP><PD><ND>{^sardu<n><m><sg>/Sardinian<n><sg>$}$ ^be<VP><p3><sg>{^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$}$}$}$

Applying rule 1 (line 56): ^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$

Applying rule 4 (line 60): ^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$}$

Applying rule 9 (line 67): ^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$}$}$

Applying rule 12 (line 71): ^Default<DP><PD><ND>{^Su<det><def><m><sg>/The<det><def><m><sg>$ ^Default<NP><PD><ND>{^sardu<n><m><sg>/Sardinian<n><sg>$}$}$ ^be<VP><p3><sg>{^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$}$}$}$

Applying rule 1 (line 56): ^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$

Applying rule 4 (line 60): ^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$}$

Applying rule 9 (line 67): ^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$}$}$

Applying rule 13 (line 72): ^Default<NP><PD><ND>{^sardu<n><m><sg>/Sardinian<n><sg>$}$ ^be<VP><p3><sg>{^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$}$}$}$

Applying output rule 11 (line 71): Be<#S><p3><sg> -> ^Default<DP><PD><ND>{^Su<det><def><m><sg>/The<det><def><m><sg>$ ^Default<NP><PD><ND>{^sardu<n><m><sg>/Sardinian<n><sg>$}$}$ ^be<VP><p3><sg>{^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$}$}$}$

Applying output rule 3 (line 60): Default<DP><p3><sg> -> ^Su<det><def><m><sg>/The<det><def><m><sg>$ ^Default<NP><PD><ND>{^sardu<n><m><sg>/Sardinian<n><sg>$}$

No rule specified: ^The<det><def><sg>$

Applying output rule 2 (line 58): Default<NP><p3><sg> -> ^sardu<n><m><sg>/Sardinian<n><sg>$

No rule specified: ^Sardinian<n><sg>$

Applying output rule 8 (line 67): be<VP><p3><sg> -> ^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$}$}$

Applying output rule 5 (line 63): be<vP><p3><sg> -> ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$

No rule specified: ^be<vbser><pres><p3><sg>$

Applying output rule 3 (line 60): default<DP><p3><sg> -> ^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$}$

No rule specified: ^a<det><ind><sg>$

Applying output rule 0 (line 56): default<NP><p3><sg> -> ^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$

No rule specified: ^ancient<adj>$

No rule specified: ^language<n><sg>$

No rule specified: ^.<sent>/.<sent>$

No rule specified: ^.<sent>/.<sent>$
^The<det><def><sg>$ ^Sardinian<n><sg>$ ^be<vbser><pres><p3><sg>$ ^a<det><ind><sg>$ ^ancient<adj>$ ^language<n><sg>$^.<sent>$^.<sent>$

==For '''Item 4: For most uses/conjugations of verbs in Sardinian, the verb stands on its own without a personal pronoun, while in English personal pronouns always precede any conjugated verbs. In other words, the tags of "appo" (I have) determine a new word "I" which precedes "have" in the English translation.'''==

Applying rule 7 (line 64): ^Àere<vbhaver><pri><p1><sg>/Have<vbhaver><pri><p1><sg>$
Applying rule 11 (line 69): ^Have<vP><p1><sg>{^Àere<vbhaver><pri><p1><sg>/Have<vbhaver><pri><p1><sg>$}$
Applying rule 15 (line 74): ^Have<VP><p1><sg>{^Have<vP><p1><sg>{^Àere<vbhaver><pri><p1><sg>/Have<vbhaver><pri><p1><sg>$}$}$
Applying rule 8 (line 65): ^pèrdere<vblex><pp><m><sg>/lose<vblex><pp><m><sg>$
Applying rule 10 (line 68): ^Have<vP><p1><sg>{^Àere<vbhaver><pri><p1><sg>/Have<vbhaver><pri><p1><sg>$}$ ^lose<vP><PD><sg>{^pèrdere<vblex><pp><m><sg>/lose<vblex><pp><m><sg>$}$
Applying rule 15 (line 74): ^Have<VP><p1><sg>{^Have<vP><p1><sg>{^Àere<vbhaver><pri><p1><sg>/Have<vbhaver><pri><p1><sg>$}$ ^lose<vP><PD><sg>{^pèrdere<vblex><pp><m><sg>/lose<vblex><pp><m><sg>$}$}$
Applying output rule 14 (line 74): Have<#S><p1><sg> -> ^Have<VP><p1><sg>{^Have<vP><p1><sg>{^Àere<vbhaver><pri><p1><sg>/Have<vbhaver><pri><p1><sg>$}$ ^lose<vP><PD><sg>{^pèrdere<vblex><pp><m><sg>/lose<vblex><pp><m><sg>$}$}$
No rule specified: ^prpers<prn><subj><p1><mf><sg>$
Applying output rule 9 (line 68): Have<VP><p1><sg> -> ^Have<vP><p1><sg>{^Àere<vbhaver><pri><p1><sg>/Have<vbhaver><pri><p1><sg>$}$ ^lose<vP><PD><sg>{^pèrdere<vblex><pp><m><sg>/lose<vblex><pp><m><sg>$}$
Applying output rule 6 (line 64): Have<vP><p1><sg> -> ^Àere<vbhaver><pri><p1><sg>/Have<vbhaver><pri><p1><sg>$
No rule specified: ^Have<vbhaver><pres><p1><sg>$=
Applying output rule 7 (line 65): lose<vP><p3><sg> -> ^pèrdere<vblex><pp><m><sg>/lose<vblex><pp><m><sg>$
No rule specified: ^lose<vblex><p3><sg>$
No rule specified: ^duos<num><m><sp>/two<num><m><sp>$
No rule specified: ^de<pr>/of<pr>$
Applying rule 3 (line 58): ^libru<n><m><pl>/book<n><pl>$
Applying rule 4 (line 60): ^su<det><def><m><pl>/the<det><def><m><pl>$ ^default<NP><PD><ND>{^libru<n><m><pl>/book<n><pl>$}$
Applying rule 1 (line 56): ^libru<n><m><pl>/book<n><pl>$ ^meu<adj><pos><m><pl>/my<det><pos><m><pl>$
Applying rule 4 (line 60): ^su<det><def><m><pl>/the<det><def><m><pl>$ ^default<NP><PD><ND>{^libru<n><m><pl>/book<n><pl>$ ^meu<adj><pos><m><pl>/my<det><pos><m><pl>$}$
Applying output rule 3 (line 60): default<DP><PD><ND> -> ^su<det><def><m><pl>/the<det><def><m><pl>$ ^default<NP><PD><ND>{^libru<n><m><pl>/book<n><pl>$ ^meu<adj><pos><m><pl>/my<det><pos><m><pl>$}$
No rule specified: ^the<det><def><pl>$
Applying output rule 0 (line 56): default<NP><p3><sg> -> ^libru<n><m><pl>/book<n><pl>$ ^meu<adj><pos><m><pl>/my<det><pos><m><pl>$
No rule specified: ^my<det>$
No rule specified: ^book<n><pl>$
No rule specified: ^.<sent>/.<sent>$
No rule specified: ^.<sent>/.<sent>$
^prpers<prn><subj><p1><mf><sg>$ ^Have<vbhaver><pres><p1><sg>$ ^lose<vblex><p3><sg>$ ^two<num><m><sp>$ ^of<pr>$ ^the<det><def><pl>$ ^my<det>$ ^book<n><pl>$^.<sent>$^.<sent>$

Sardinian and English/Structural transfer

2023-05-04T15:35:57Z

Rorlija1: /* Item 2: Noun-adjective order in noun phraseology: adjectives now come before the noun in translations when necessary: */

==pre-evaluation==
*WER, PER, and other useful numbers:
Statistics about input files
-------------------------------------------------------
Number of words in reference: 81
Number of words in test: 80
Number of unknown words (marked with a star) in test: 14
Percentage of unknown words: 17.50 %

Results when removing unknown-word marks (stars)
-------------------------------------------------------
Edit distance: 77
Word error rate (WER): 95.06 %
Number of position-independent correct words: 12
Position-independent word error rate (PER): 85.19 %
*coverage from monolingual transducer on srd.tests:
Coverage: 97.78%
Top unknown words in the corpus:
1 paìsu
1 Lettu
*coverage from bilingual transducer on srd.tests:
Number of tokenised words in the corpus: 91
Coverage: 84.62%
Top unknown words in the corpus:
2 bellu
1 paisu
1 paìsu
1 Lettu
1 furatu
1 dinari
1 punitos
1 rica
1 datu
1 milli
1 francos
1 betzu
1 iscimpru

==.rtx rules==
====Item 1: Determiners before nouns in Sardinian are omitted in English translations that do not include determiners before nouns====
*Ex: {{transferTest|srd|eng|Sa Frantza est unu paisu bellu.|France is a beautiful country.}}
*Outputs for:
*:tagger: ^Su<det><def><f><sg>$ ^Frantza<np><top><f><sg>$ ^èssere<vbser><pri><p3><sg>$ ^unu<det><ind><m><sg>$ ^paisu<n><m><sg>$ ^bellu<adj><m><sg>$^.<sent>$^.<sent>$
*:lex:
1:SELECT:0.8:Su<det><def><f><sg>:2:The<det><def><f><sg>
^Su<det><def><f><sg>/The<det><def><f><sg>$ ^Frantza<np><top><f><sg>/France<np><top><f><sg>$ ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$ ^unu<det><ind><m><sg>/a<det><ind><m><sg>$ ^paisu<n><m><sg>/country<n><sg>$ ^bellu<adj><m><sg>/beautiful<adj><m><sg>$^.<sent>/.<sent>$^.<sent>/.<sent>$
*:transfer:
Applying rule 4 (line 58): ^Su<det><def><f><sg>/The<det><def><f><sg>$ ^Frantza<np><top><f><sg>/France<np><top><f><sg>$
Applying rule 6 (line 61): ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$
Applying rule 1 (line 54): ^paisu<n><m><sg>/country<n><sg>$ ^bellu<adj><m><sg>/beautiful<adj><m><sg>$
Applying rule 3 (line 57): ^unu<det><ind><m><sg>/a<det><ind><m><sg>$ ^default<NP><PD><ND>{^paisu<n><m><sg>/country<n><sg>$ ^bellu<adj><m><sg>/beautiful<adj><m><sg>$}$
Applying rule 8 (line 64): ^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><m><sg>/a<det><ind><m><sg>$ ^default<NP><PD><ND>{^paisu<n><m><sg>/country<n><sg>$ ^bellu<adj><m><sg>/beautiful<adj><m><sg>$}$}$
Applying rule 9 (line 66): ^Default<DP><PD><ND>{^Su<det><def><f><sg>/The<det><def><f><sg>$ ^Frantza<np><top><f><sg>/France<np><top><f><sg>$}$ ^be<VP><p3><sg>{^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><m><sg>/a<det><ind><m><sg>$ ^default<NP><PD><ND>{^paisu<n><m><sg>/country<n><sg>$ ^bellu<adj><m><sg>/beautiful<adj><m><sg>$}$}$}$
Applying output rule 8 (line 66): Be<#S><p3><sg> -> ^Default<DP><PD><ND>{^Su<det><def><f><sg>/The<det><def><f><sg>$ ^Frantza<np><top><f><sg>/France<np><top><f><sg>$}$ ^be<VP><p3><sg>{^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><m><sg>/a<det><ind><m><sg>$ ^default<NP><PD><ND>{^paisu<n><m><sg>/country<n><sg>$ ^bellu<adj><m><sg>/beautiful<adj><m><sg>$}$}$}$
Applying output rule 3 (line 58): Default<DP><p3><sg> -> ^Su<det><def><f><sg>/The<det><def><f><sg>$ ^Frantza<np><top><f><sg>/France<np><top><f><sg>$
No rule specified: ^France<np><top><sg>$
Applying output rule 7 (line 64): be<VP><p3><sg> -> ^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><m><sg>/a<det><ind><m><sg>$ ^default<NP><PD><ND>{^paisu<n><m><sg>/country<n><sg>$ ^bellu<adj><m><sg>/beautiful<adj><m><sg>$}$}$
Applying output rule 5 (line 61): be<vP><p3><sg> -> ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$
No rule specified: ^be<vbser><pres><p3><sg>$
Applying output rule 2 (line 57): default<DP><p3><sg> -> ^unu<det><ind><m><sg>/a<det><ind><m><sg>$ ^default<NP><PD><ND>{^paisu<n><m><sg>/country<n><sg>$ ^bellu<adj><m><sg>/beautiful<adj><m><sg>$}$
No rule specified: ^a<det><ind><sg>$
Applying output rule 0 (line 54): default<NP><p3><sg> -> ^paisu<n><m><sg>/country<n><sg>$ ^bellu<adj><m><sg>/beautiful<adj><m><sg>$
No rule specified: ^beautiful<adj>$
No rule specified: ^country<n><sg>$
No rule specified: ^.<sent>/.<sent>$
No rule specified: ^.<sent>/.<sent>$
^France<np><top><sg>$ ^be<vbser><pres><p3><sg>$ ^a<det><ind><sg>$ ^beautiful<adj>$ ^country<n><sg>$^.<sent>$^.<sent>$
*:abc-xyz:
France is a beautiful country.

====Item 2: Noun-adjective order in noun phraseology: adjectives now come before the noun in translations when necessary:====
*Ex: {{transferTest|srd|eng|Su sardu est una limba antica.|Sardinian is an ancient language.}}
*Outputs for:
*:tagger: ^Su<det><def><m><sg>$ ^sardu<n><m><sg>$ ^èssere<vbser><pri><p3><sg>$ ^unu<det><ind><f><sg>$ ^limba<n><f><sg>$ ^anticu<adj><f><sg>$^.<sent>$^.<sent>$
*:lex:
1:SELECT:0.8:Su<det><def><m><sg>:2:The<det><def><m><sg>
^Su<det><def><m><sg>/The<det><def><m><sg>$ ^sardu<n><m><sg>/Sardinian<n><sg>$ ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$ ^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$^.<sent>/.<sent>$^.<sent>/.<sent>$
*:transfer: [https://wikis.swarthmore.edu/ling073/Sardinian_and_English/Structural_transfer_output at this link]
*:abc-xyz:
The Sardinian is an ancient language.

====Item 3: Posessive determiner/marker order in noun phraseology====
*Ex: {{transferTest|srd|eng|Libru meu est.|It is my book.}}
*Outputs for:
*:tagger: ^Libru<n><m><sg>$ ^meu<adj><pos><m><sg>$ ^èssere<vbser><pri><p3><sg>$^.<sent>$^.<sent>$
*:lex: ^Libru<n><m><sg>/Book<n><sg>$ ^meu<adj><pos><m><sg>/my<det><pos><m><sg>$ ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$^.<sent>/.<sent>$^.<sent>/.<sent>$
*:transfer:
Applying rule 3 (line 58): ^Libru<n><m><sg>/Book<n><sg>$
Applying rule 1 (line 56): ^Libru<n><m><sg>/Book<n><sg>$ ^meu<adj><pos><m><sg>/my<det><pos><m><sg>$
Applying rule 6 (line 63): ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$
Applying rule 11 (line 69): ^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$
Applying rule 13 (line 72): ^Default<NP><PD><ND>{^Libru<n><m><sg>/Book<n><sg>$ ^meu<adj><pos><m><sg>/my<det><pos><m><sg>$}$ ^be<VP><p3><sg>{^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$}$
Applying output rule 12 (line 72): Be<#S><p3><sg> -> ^Default<NP><PD><ND>{^Libru<n><m><sg>/Book<n><sg>$ ^meu<adj><pos><m><sg>/my<det><pos><m><sg>$}$ ^be<VP><p3><sg>{^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$}$
Applying output rule 0 (line 56): Default<NP><p3><sg> -> ^Libru<n><m><sg>/Book<n><sg>$ ^meu<adj><pos><m><sg>/my<det><pos><m><sg>$
No rule specified: ^my<det>$
No rule specified: ^Book<n><sg>$
Applying output rule 10 (line 69): be<VP><p3><sg> -> ^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$
Applying output rule 5 (line 63): be<vP><p3><sg> -> ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$
No rule specified: ^be<vbser><pres><p3><sg>$
No rule specified: ^.<sent>/.<sent>$
No rule specified: ^.<sent>/.<sent>$
^my<det>$ ^Book<n><sg>$ ^be<vbser><pres><p3><sg>$^.<sent>$^.<sent>$
*:abc-xyz:
#my Book is.

====Item 4: For most uses/conjugations of verbs in Sardinian, the verb stands on its own without a personal pronoun, while in English personal pronouns always precede any conjugated verbs. In other words, the tags of "appo" (I have) determine a new word "I" which precedes "have" in the English translation.====
*Ex: {{transferTest|srd|eng|Appo pèrditu duos de sos libros meos.|I have lost two of my books.}}
*Outputs for:
*:tagger: ^Àere<vbhaver><pri><p1><sg>$ ^pèrdere<vblex><pp><m><sg>$ ^duos<num><m><sp>$ ^de<pr>$ ^su<det><def><m><pl>$ ^libru<n><m><pl>$ ^meu<adj><pos><m><pl>$^.<sent>$^.<sent>$
*:lex:
1:SELECT:1:de<pr>:2:of<pr>
1:SELECT:0.8:su<det><def><m><pl>:2:the<det><def><m><pl>
^Àere<vbhaver><pri><p1><sg>/Have<vbhaver><pri><p1><sg>$ ^pèrdere<vblex><pp><m><sg>/lose<vblex><pp><m><sg>$ ^duos<num><m><sp>/two<num><m><sp>$ ^de<pr>/of<pr>$ ^su<det><def><m><pl>/the<det><def><m><pl>$ ^libru<n><m><pl>/book<n><pl>$ ^meu<adj><pos><m><pl>/my<det><pos><m><pl>$^.<sent>/.<sent>$^.<sent>/.<sent>$
*:transfer:
Applying rule 7 (line 64): ^Àere<vbhaver><pri><p1><sg>/Have<vbhaver><pri><p1><sg>$
Applying rule 11 (line 69): ^Have<vP><p1><sg>{^Àere<vbhaver><pri><p1><sg>/Have<vbhaver><pri><p1><sg>$}$
Applying rule 15 (line 74): ^Have<VP><p1><sg>{^Have<vP><p1><sg>{^Àere<vbhaver><pri><p1><sg>/Have<vbhaver><pri><p1><sg>$}$}$
Applying rule 8 (line 65): ^pèrdere<vblex><pp><m><sg>/lose<vblex><pp><m><sg>$
Applying rule 10 (line 68): ^Have<vP><p1><sg>{^Àere<vbhaver><pri><p1><sg>/Have<vbhaver><pri><p1><sg>$}$ ^lose<vP><PD><sg>{^pèrdere<vblex><pp><m><sg>/lose<vblex><pp><m><sg>$}$
Applying rule 15 (line 74): ^Have<VP><p1><sg>{^Have<vP><p1><sg>{^Àere<vbhaver><pri><p1><sg>/Have<vbhaver><pri><p1><sg>$}$ ^lose<vP><PD><sg>{^pèrdere<vblex><pp><m><sg>/lose<vblex><pp><m><sg>$}$}$
Applying output rule 14 (line 74): Have<#S><p1><sg> -> ^Have<VP><p1><sg>{^Have<vP><p1><sg>{^Àere<vbhaver><pri><p1><sg>/Have<vbhaver><pri><p1><sg>$}$ ^lose<vP><PD><sg>{^pèrdere<vblex><pp><m><sg>/lose<vblex><pp><m><sg>$}$}$
No rule specified: ^prpers<prn><subj><p1><mf><sg>$
Applying output rule 9 (line 68): Have<VP><p1><sg> -> ^Have<vP><p1><sg>{^Àere<vbhaver><pri><p1><sg>/Have<vbhaver><pri><p1><sg>$}$ ^lose<vP><PD><sg>{^pèrdere<vblex><pp><m><sg>/lose<vblex><pp><m><sg>$}$
Applying output rule 6 (line 64): Have<vP><p1><sg> -> ^Àere<vbhaver><pri><p1><sg>/Have<vbhaver><pri><p1><sg>$
No rule specified: ^Have<vbhaver><pres><p1><sg>$=
Applying output rule 7 (line 65): lose<vP><p3><sg> -> ^pèrdere<vblex><pp><m><sg>/lose<vblex><pp><m><sg>$
No rule specified: ^lose<vblex><p3><sg>$
No rule specified: ^duos<num><m><sp>/two<num><m><sp>$
No rule specified: ^de<pr>/of<pr>$
Applying rule 3 (line 58): ^libru<n><m><pl>/book<n><pl>$
Applying rule 4 (line 60): ^su<det><def><m><pl>/the<det><def><m><pl>$ ^default<NP><PD><ND>{^libru<n><m><pl>/book<n><pl>$}$
Applying rule 1 (line 56): ^libru<n><m><pl>/book<n><pl>$ ^meu<adj><pos><m><pl>/my<det><pos><m><pl>$
Applying rule 4 (line 60): ^su<det><def><m><pl>/the<det><def><m><pl>$ ^default<NP><PD><ND>{^libru<n><m><pl>/book<n><pl>$ ^meu<adj><pos><m><pl>/my<det><pos><m><pl>$}$
Applying output rule 3 (line 60): default<DP><PD><ND> -> ^su<det><def><m><pl>/the<det><def><m><pl>$ ^default<NP><PD><ND>{^libru<n><m><pl>/book<n><pl>$ ^meu<adj><pos><m><pl>/my<det><pos><m><pl>$}$
No rule specified: ^the<det><def><pl>$
Applying output rule 0 (line 56): default<NP><p3><sg> -> ^libru<n><m><pl>/book<n><pl>$ ^meu<adj><pos><m><pl>/my<det><pos><m><pl>$
No rule specified: ^my<det>$
No rule specified: ^book<n><pl>$
No rule specified: ^.<sent>/.<sent>$
No rule specified: ^.<sent>/.<sent>$
^prpers<prn><subj><p1><mf><sg>$ ^Have<vbhaver><pres><p1><sg>$ ^lose<vblex><p3><sg>$ ^two<num><m><sp>$ ^of<pr>$ ^the<det><def><pl>$ ^my<det>$ ^book<n><pl>$^.<sent>$^.<sent>$
*:abc-xyz:
I #Have #lose #two of the #my books.

==post evaluation==
*WER, PER, and other useful numbers, part 2:
*Coverage from monolingual transducer, part 2:
*Coverage from bilingual transducer, part 2:

[[Category:Sp23_StructuralTransfer]],[[Category:Sardinian]],[[Category:English]]

Sardinian and English/Structural transfer output

2023-05-04T15:35:33Z

Rorlija1:

Given that the output of the srd-eng-transfer is quite lengthy in some instances, I've opted to create this page to reduce clutter on the main structural transfer page.

For '''Item 2: Noun-adjective order in noun phraseology: adjectives now come before the noun in translations when necessary:'''

Applying rule 3 (line 58): ^sardu<n><m><sg>/Sardinian<n><sg>$

Applying rule 4 (line 60): ^Su<det><def><m><sg>/The<det><def><m><sg>$ ^Default<NP><PD><ND>{^sardu<n><m><sg>/Sardinian<n><sg>$}$

Applying rule 6 (line 63): ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$

Applying rule 11 (line 69): ^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$

Applying rule 12 (line 71): ^Default<DP><PD><ND>{^Su<det><def><m><sg>/The<det><def><m><sg>$ ^Default<NP><PD><ND>{^sardu<n><m><sg>/Sardinian<n><sg>$}$}$ ^be<VP><p3><sg>{^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$}$

Applying rule 6 (line 63): ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$

Applying rule 11 (line 69): ^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$

Applying rule 13 (line 72): ^Default<NP><PD><ND>{^sardu<n><m><sg>/Sardinian<n><sg>$}$ ^be<VP><p3><sg>{^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$}$

Applying rule 3 (line 58): ^limba<n><f><sg>/language<n><sg>$

Applying rule 4 (line 60): ^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$}$

Applying rule 9 (line 67): ^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$}$}$

Applying rule 12 (line 71): ^Default<DP><PD><ND>{^Su<det><def><m><sg>/The<det><def><m><sg>$ ^Default<NP><PD><ND>{^sardu<n><m><sg>/Sardinian<n><sg>$}$}$ ^be<VP><p3><sg>{^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$}$}$}$

Applying rule 3 (line 58): ^limba<n><f><sg>/language<n><sg>$

Applying rule 4 (line 60): ^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$}$

Applying rule 9 (line 67): ^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$}$}$

Applying rule 13 (line 72): ^Default<NP><PD><ND>{^sardu<n><m><sg>/Sardinian<n><sg>$}$ ^be<VP><p3><sg>{^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$}$}$}$

Applying rule 1 (line 56): ^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$

Applying rule 4 (line 60): ^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$}$

Applying rule 9 (line 67): ^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$}$}$

Applying rule 12 (line 71): ^Default<DP><PD><ND>{^Su<det><def><m><sg>/The<det><def><m><sg>$ ^Default<NP><PD><ND>{^sardu<n><m><sg>/Sardinian<n><sg>$}$}$ ^be<VP><p3><sg>{^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$}$}$}$

Applying rule 1 (line 56): ^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$

Applying rule 4 (line 60): ^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$}$

Applying rule 9 (line 67): ^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$}$}$

Applying rule 13 (line 72): ^Default<NP><PD><ND>{^sardu<n><m><sg>/Sardinian<n><sg>$}$ ^be<VP><p3><sg>{^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$}$}$}$

Applying output rule 11 (line 71): Be<#S><p3><sg> -> ^Default<DP><PD><ND>{^Su<det><def><m><sg>/The<det><def><m><sg>$ ^Default<NP><PD><ND>{^sardu<n><m><sg>/Sardinian<n><sg>$}$}$ ^be<VP><p3><sg>{^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$}$}$}$

Applying output rule 3 (line 60): Default<DP><p3><sg> -> ^Su<det><def><m><sg>/The<det><def><m><sg>$ ^Default<NP><PD><ND>{^sardu<n><m><sg>/Sardinian<n><sg>$}$

No rule specified: ^The<det><def><sg>$

Applying output rule 2 (line 58): Default<NP><p3><sg> -> ^sardu<n><m><sg>/Sardinian<n><sg>$

No rule specified: ^Sardinian<n><sg>$

Applying output rule 8 (line 67): be<VP><p3><sg> -> ^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$}$}$

Applying output rule 5 (line 63): be<vP><p3><sg> -> ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$

No rule specified: ^be<vbser><pres><p3><sg>$

Applying output rule 3 (line 60): default<DP><p3><sg> -> ^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$}$

No rule specified: ^a<det><ind><sg>$

Applying output rule 0 (line 56): default<NP><p3><sg> -> ^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$

No rule specified: ^ancient<adj>$

No rule specified: ^language<n><sg>$

No rule specified: ^.<sent>/.<sent>$

No rule specified: ^.<sent>/.<sent>$
^The<det><def><sg>$ ^Sardinian<n><sg>$ ^be<vbser><pres><p3><sg>$ ^a<det><ind><sg>$ ^ancient<adj>$ ^language<n><sg>$^.<sent>$^.<sent>$

Sardinian and English/Structural transfer output

2023-05-04T15:35:11Z

Rorlija1: creating

Given that the output of the srd-eng-transfer is quite lengthy in some instances, I've opted to create this page to reduce clutter on the main structural transfer page.

For '''Item 2: Noun-adjective order in noun phraseology: adjectives now come before the noun in translations when necessary:'''

Applying rule 3 (line 58): ^sardu<n><m><sg>/Sardinian<n><sg>$

Applying rule 4 (line 60): ^Su<det><def><m><sg>/The<det><def><m><sg>$ ^Default<NP><PD><ND>{^sardu<n><m><sg>/Sardinian<n><sg>$}$

Applying rule 6 (line 63): ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$

Applying rule 11 (line 69): ^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$

Applying rule 12 (line 71): ^Default<DP><PD><ND>{^Su<det><def><m><sg>/The<det><def><m><sg>$ ^Default<NP><PD><ND>{^sardu<n><m><sg>/Sardinian<n><sg>$}$}$ ^be<VP><p3><sg>{^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$}$

Applying rule 6 (line 63): ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$

Applying rule 11 (line 69): ^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$

Applying rule 13 (line 72): ^Default<NP><PD><ND>{^sardu<n><m><sg>/Sardinian<n><sg>$}$ ^be<VP><p3><sg>{^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$}$

Applying rule 3 (line 58): ^limba<n><f><sg>/language<n><sg>$

Applying rule 4 (line 60): ^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$}$

Applying rule 9 (line 67): ^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$}$}$

Applying rule 12 (line 71): ^Default<DP><PD><ND>{^Su<det><def><m><sg>/The<det><def><m><sg>$ ^Default<NP><PD><ND>{^sardu<n><m><sg>/Sardinian<n><sg>$}$}$ ^be<VP><p3><sg>{^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$}$}$}$

Applying rule 3 (line 58): ^limba<n><f><sg>/language<n><sg>$

Applying rule 4 (line 60): ^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$}$

Applying rule 9 (line 67): ^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$}$}$

Applying rule 13 (line 72): ^Default<NP><PD><ND>{^sardu<n><m><sg>/Sardinian<n><sg>$}$ ^be<VP><p3><sg>{^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$}$}$}$

Applying rule 1 (line 56): ^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$

Applying rule 4 (line 60): ^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$}$

Applying rule 9 (line 67): ^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$}$}$

Applying rule 12 (line 71): ^Default<DP><PD><ND>{^Su<det><def><m><sg>/The<det><def><m><sg>$ ^Default<NP><PD><ND>{^sardu<n><m><sg>/Sardinian<n><sg>$}$}$ ^be<VP><p3><sg>{^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$}$}$}$

Applying rule 1 (line 56): ^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$

Applying rule 4 (line 60): ^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$}$

Applying rule 9 (line 67): ^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$}$}$

Applying rule 13 (line 72): ^Default<NP><PD><ND>{^sardu<n><m><sg>/Sardinian<n><sg>$}$ ^be<VP><p3><sg>{^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$}$}$}$

Applying output rule 11 (line 71): Be<S><p3><sg> -> ^Default<DP><PD><ND>{^Su<det><def><m><sg>/The<det><def><m><sg>$ ^Default<NP><PD><ND>{^sardu<n><m><sg>/Sardinian<n><sg>$}$}$ ^be<VP><p3><sg>{^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$}$}$}$

Applying output rule 3 (line 60): Default<DP><p3><sg> -> ^Su<det><def><m><sg>/The<det><def><m><sg>$ ^Default<NP><PD><ND>{^sardu<n><m><sg>/Sardinian<n><sg>$}$

No rule specified: ^The<det><def><sg>$

Applying output rule 2 (line 58): Default<NP><p3><sg> -> ^sardu<n><m><sg>/Sardinian<n><sg>$

No rule specified: ^Sardinian<n><sg>$

Applying output rule 8 (line 67): be<VP><p3><sg> -> ^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$}$}$

Applying output rule 5 (line 63): be<vP><p3><sg> -> ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$

No rule specified: ^be<vbser><pres><p3><sg>$

Applying output rule 3 (line 60): default<DP><p3><sg> -> ^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$}$

No rule specified: ^a<det><ind><sg>$

Applying output rule 0 (line 56): default<NP><p3><sg> -> ^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$

No rule specified: ^ancient<adj>$

No rule specified: ^language<n><sg>$

No rule specified: ^.<sent>/.<sent>$

No rule specified: ^.<sent>/.<sent>$
^The<det><def><sg>$ ^Sardinian<n><sg>$ ^be<vbser><pres><p3><sg>$ ^a<det><ind><sg>$ ^ancient<adj>$ ^language<n><sg>$^.<sent>$^.<sent>$

Sardinian and English/Structural transfer

2023-05-04T15:32:09Z

Rorlija1: /* Item 2: Noun-adjective order in noun phraseology: adjectives now come before the noun in translations when necessary: */

==pre-evaluation==
*WER, PER, and other useful numbers:
Statistics about input files
-------------------------------------------------------
Number of words in reference: 81
Number of words in test: 80
Number of unknown words (marked with a star) in test: 14
Percentage of unknown words: 17.50 %

Results when removing unknown-word marks (stars)
-------------------------------------------------------
Edit distance: 77
Word error rate (WER): 95.06 %
Number of position-independent correct words: 12
Position-independent word error rate (PER): 85.19 %
*coverage from monolingual transducer on srd.tests:
Coverage: 97.78%
Top unknown words in the corpus:
1 paìsu
1 Lettu
*coverage from bilingual transducer on srd.tests:
Number of tokenised words in the corpus: 91
Coverage: 84.62%
Top unknown words in the corpus:
2 bellu
1 paisu
1 paìsu
1 Lettu
1 furatu
1 dinari
1 punitos
1 rica
1 datu
1 milli
1 francos
1 betzu
1 iscimpru

==.rtx rules==
====Item 1: Determiners before nouns in Sardinian are omitted in English translations that do not include determiners before nouns====
*Ex: {{transferTest|srd|eng|Sa Frantza est unu paisu bellu.|France is a beautiful country.}}
*Outputs for:
*:tagger: ^Su<det><def><f><sg>$ ^Frantza<np><top><f><sg>$ ^èssere<vbser><pri><p3><sg>$ ^unu<det><ind><m><sg>$ ^paisu<n><m><sg>$ ^bellu<adj><m><sg>$^.<sent>$^.<sent>$
*:lex:
1:SELECT:0.8:Su<det><def><f><sg>:2:The<det><def><f><sg>
^Su<det><def><f><sg>/The<det><def><f><sg>$ ^Frantza<np><top><f><sg>/France<np><top><f><sg>$ ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$ ^unu<det><ind><m><sg>/a<det><ind><m><sg>$ ^paisu<n><m><sg>/country<n><sg>$ ^bellu<adj><m><sg>/beautiful<adj><m><sg>$^.<sent>/.<sent>$^.<sent>/.<sent>$
*:transfer:
Applying rule 4 (line 58): ^Su<det><def><f><sg>/The<det><def><f><sg>$ ^Frantza<np><top><f><sg>/France<np><top><f><sg>$
Applying rule 6 (line 61): ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$
Applying rule 1 (line 54): ^paisu<n><m><sg>/country<n><sg>$ ^bellu<adj><m><sg>/beautiful<adj><m><sg>$
Applying rule 3 (line 57): ^unu<det><ind><m><sg>/a<det><ind><m><sg>$ ^default<NP><PD><ND>{^paisu<n><m><sg>/country<n><sg>$ ^bellu<adj><m><sg>/beautiful<adj><m><sg>$}$
Applying rule 8 (line 64): ^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><m><sg>/a<det><ind><m><sg>$ ^default<NP><PD><ND>{^paisu<n><m><sg>/country<n><sg>$ ^bellu<adj><m><sg>/beautiful<adj><m><sg>$}$}$
Applying rule 9 (line 66): ^Default<DP><PD><ND>{^Su<det><def><f><sg>/The<det><def><f><sg>$ ^Frantza<np><top><f><sg>/France<np><top><f><sg>$}$ ^be<VP><p3><sg>{^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><m><sg>/a<det><ind><m><sg>$ ^default<NP><PD><ND>{^paisu<n><m><sg>/country<n><sg>$ ^bellu<adj><m><sg>/beautiful<adj><m><sg>$}$}$}$
Applying output rule 8 (line 66): Be<#S><p3><sg> -> ^Default<DP><PD><ND>{^Su<det><def><f><sg>/The<det><def><f><sg>$ ^Frantza<np><top><f><sg>/France<np><top><f><sg>$}$ ^be<VP><p3><sg>{^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><m><sg>/a<det><ind><m><sg>$ ^default<NP><PD><ND>{^paisu<n><m><sg>/country<n><sg>$ ^bellu<adj><m><sg>/beautiful<adj><m><sg>$}$}$}$
Applying output rule 3 (line 58): Default<DP><p3><sg> -> ^Su<det><def><f><sg>/The<det><def><f><sg>$ ^Frantza<np><top><f><sg>/France<np><top><f><sg>$
No rule specified: ^France<np><top><sg>$
Applying output rule 7 (line 64): be<VP><p3><sg> -> ^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><m><sg>/a<det><ind><m><sg>$ ^default<NP><PD><ND>{^paisu<n><m><sg>/country<n><sg>$ ^bellu<adj><m><sg>/beautiful<adj><m><sg>$}$}$
Applying output rule 5 (line 61): be<vP><p3><sg> -> ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$
No rule specified: ^be<vbser><pres><p3><sg>$
Applying output rule 2 (line 57): default<DP><p3><sg> -> ^unu<det><ind><m><sg>/a<det><ind><m><sg>$ ^default<NP><PD><ND>{^paisu<n><m><sg>/country<n><sg>$ ^bellu<adj><m><sg>/beautiful<adj><m><sg>$}$
No rule specified: ^a<det><ind><sg>$
Applying output rule 0 (line 54): default<NP><p3><sg> -> ^paisu<n><m><sg>/country<n><sg>$ ^bellu<adj><m><sg>/beautiful<adj><m><sg>$
No rule specified: ^beautiful<adj>$
No rule specified: ^country<n><sg>$
No rule specified: ^.<sent>/.<sent>$
No rule specified: ^.<sent>/.<sent>$
^France<np><top><sg>$ ^be<vbser><pres><p3><sg>$ ^a<det><ind><sg>$ ^beautiful<adj>$ ^country<n><sg>$^.<sent>$^.<sent>$
*:abc-xyz:
France is a beautiful country.

====Item 2: Noun-adjective order in noun phraseology: adjectives now come before the noun in translations when necessary:====
*Ex: {{transferTest|srd|eng|Su sardu est una limba antica.|Sardinian is an ancient language.}}
*Outputs for:
*:tagger: ^Su<det><def><m><sg>$ ^sardu<n><m><sg>$ ^èssere<vbser><pri><p3><sg>$ ^unu<det><ind><f><sg>$ ^limba<n><f><sg>$ ^anticu<adj><f><sg>$^.<sent>$^.<sent>$
*:lex:
1:SELECT:0.8:Su<det><def><m><sg>:2:The<det><def><m><sg>
^Su<det><def><m><sg>/The<det><def><m><sg>$ ^sardu<n><m><sg>/Sardinian<n><sg>$ ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$ ^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$^.<sent>/.<sent>$^.<sent>/.<sent>$
*:transfer: [
*:abc-xyz:
The Sardinian is an ancient language.

====Item 3: Posessive determiner/marker order in noun phraseology====
*Ex: {{transferTest|srd|eng|Libru meu est.|It is my book.}}
*Outputs for:
*:tagger: ^Libru<n><m><sg>$ ^meu<adj><pos><m><sg>$ ^èssere<vbser><pri><p3><sg>$^.<sent>$^.<sent>$
*:lex: ^Libru<n><m><sg>/Book<n><sg>$ ^meu<adj><pos><m><sg>/my<det><pos><m><sg>$ ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$^.<sent>/.<sent>$^.<sent>/.<sent>$
*:transfer:
Applying rule 3 (line 58): ^Libru<n><m><sg>/Book<n><sg>$
Applying rule 1 (line 56): ^Libru<n><m><sg>/Book<n><sg>$ ^meu<adj><pos><m><sg>/my<det><pos><m><sg>$
Applying rule 6 (line 63): ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$
Applying rule 11 (line 69): ^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$
Applying rule 13 (line 72): ^Default<NP><PD><ND>{^Libru<n><m><sg>/Book<n><sg>$ ^meu<adj><pos><m><sg>/my<det><pos><m><sg>$}$ ^be<VP><p3><sg>{^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$}$
Applying output rule 12 (line 72): Be<#S><p3><sg> -> ^Default<NP><PD><ND>{^Libru<n><m><sg>/Book<n><sg>$ ^meu<adj><pos><m><sg>/my<det><pos><m><sg>$}$ ^be<VP><p3><sg>{^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$}$
Applying output rule 0 (line 56): Default<NP><p3><sg> -> ^Libru<n><m><sg>/Book<n><sg>$ ^meu<adj><pos><m><sg>/my<det><pos><m><sg>$
No rule specified: ^my<det>$
No rule specified: ^Book<n><sg>$
Applying output rule 10 (line 69): be<VP><p3><sg> -> ^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$
Applying output rule 5 (line 63): be<vP><p3><sg> -> ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$
No rule specified: ^be<vbser><pres><p3><sg>$
No rule specified: ^.<sent>/.<sent>$
No rule specified: ^.<sent>/.<sent>$
^my<det>$ ^Book<n><sg>$ ^be<vbser><pres><p3><sg>$^.<sent>$^.<sent>$
*:abc-xyz:
#my Book is.

====Item 4: For most uses/conjugations of verbs in Sardinian, the verb stands on its own without a personal pronoun, while in English personal pronouns always precede any conjugated verbs. In other words, the tags of "appo" (I have) determine a new word "I" which precedes "have" in the English translation.====
*Ex: {{transferTest|srd|eng|Appo pèrditu duos de sos libros meos.|I have lost two of my books.}}
*Outputs for:
*:tagger: ^Àere<vbhaver><pri><p1><sg>$ ^pèrdere<vblex><pp><m><sg>$ ^duos<num><m><sp>$ ^de<pr>$ ^su<det><def><m><pl>$ ^libru<n><m><pl>$ ^meu<adj><pos><m><pl>$^.<sent>$^.<sent>$
*:lex:
1:SELECT:1:de<pr>:2:of<pr>
1:SELECT:0.8:su<det><def><m><pl>:2:the<det><def><m><pl>
^Àere<vbhaver><pri><p1><sg>/Have<vbhaver><pri><p1><sg>$ ^pèrdere<vblex><pp><m><sg>/lose<vblex><pp><m><sg>$ ^duos<num><m><sp>/two<num><m><sp>$ ^de<pr>/of<pr>$ ^su<det><def><m><pl>/the<det><def><m><pl>$ ^libru<n><m><pl>/book<n><pl>$ ^meu<adj><pos><m><pl>/my<det><pos><m><pl>$^.<sent>/.<sent>$^.<sent>/.<sent>$
*:transfer:
Applying rule 7 (line 64): ^Àere<vbhaver><pri><p1><sg>/Have<vbhaver><pri><p1><sg>$
Applying rule 11 (line 69): ^Have<vP><p1><sg>{^Àere<vbhaver><pri><p1><sg>/Have<vbhaver><pri><p1><sg>$}$
Applying rule 15 (line 74): ^Have<VP><p1><sg>{^Have<vP><p1><sg>{^Àere<vbhaver><pri><p1><sg>/Have<vbhaver><pri><p1><sg>$}$}$
Applying rule 8 (line 65): ^pèrdere<vblex><pp><m><sg>/lose<vblex><pp><m><sg>$
Applying rule 10 (line 68): ^Have<vP><p1><sg>{^Àere<vbhaver><pri><p1><sg>/Have<vbhaver><pri><p1><sg>$}$ ^lose<vP><PD><sg>{^pèrdere<vblex><pp><m><sg>/lose<vblex><pp><m><sg>$}$
Applying rule 15 (line 74): ^Have<VP><p1><sg>{^Have<vP><p1><sg>{^Àere<vbhaver><pri><p1><sg>/Have<vbhaver><pri><p1><sg>$}$ ^lose<vP><PD><sg>{^pèrdere<vblex><pp><m><sg>/lose<vblex><pp><m><sg>$}$}$
Applying output rule 14 (line 74): Have<#S><p1><sg> -> ^Have<VP><p1><sg>{^Have<vP><p1><sg>{^Àere<vbhaver><pri><p1><sg>/Have<vbhaver><pri><p1><sg>$}$ ^lose<vP><PD><sg>{^pèrdere<vblex><pp><m><sg>/lose<vblex><pp><m><sg>$}$}$
No rule specified: ^prpers<prn><subj><p1><mf><sg>$
Applying output rule 9 (line 68): Have<VP><p1><sg> -> ^Have<vP><p1><sg>{^Àere<vbhaver><pri><p1><sg>/Have<vbhaver><pri><p1><sg>$}$ ^lose<vP><PD><sg>{^pèrdere<vblex><pp><m><sg>/lose<vblex><pp><m><sg>$}$
Applying output rule 6 (line 64): Have<vP><p1><sg> -> ^Àere<vbhaver><pri><p1><sg>/Have<vbhaver><pri><p1><sg>$
No rule specified: ^Have<vbhaver><pres><p1><sg>$=
Applying output rule 7 (line 65): lose<vP><p3><sg> -> ^pèrdere<vblex><pp><m><sg>/lose<vblex><pp><m><sg>$
No rule specified: ^lose<vblex><p3><sg>$
No rule specified: ^duos<num><m><sp>/two<num><m><sp>$
No rule specified: ^de<pr>/of<pr>$
Applying rule 3 (line 58): ^libru<n><m><pl>/book<n><pl>$
Applying rule 4 (line 60): ^su<det><def><m><pl>/the<det><def><m><pl>$ ^default<NP><PD><ND>{^libru<n><m><pl>/book<n><pl>$}$
Applying rule 1 (line 56): ^libru<n><m><pl>/book<n><pl>$ ^meu<adj><pos><m><pl>/my<det><pos><m><pl>$
Applying rule 4 (line 60): ^su<det><def><m><pl>/the<det><def><m><pl>$ ^default<NP><PD><ND>{^libru<n><m><pl>/book<n><pl>$ ^meu<adj><pos><m><pl>/my<det><pos><m><pl>$}$
Applying output rule 3 (line 60): default<DP><PD><ND> -> ^su<det><def><m><pl>/the<det><def><m><pl>$ ^default<NP><PD><ND>{^libru<n><m><pl>/book<n><pl>$ ^meu<adj><pos><m><pl>/my<det><pos><m><pl>$}$
No rule specified: ^the<det><def><pl>$
Applying output rule 0 (line 56): default<NP><p3><sg> -> ^libru<n><m><pl>/book<n><pl>$ ^meu<adj><pos><m><pl>/my<det><pos><m><pl>$
No rule specified: ^my<det>$
No rule specified: ^book<n><pl>$
No rule specified: ^.<sent>/.<sent>$
No rule specified: ^.<sent>/.<sent>$
^prpers<prn><subj><p1><mf><sg>$ ^Have<vbhaver><pres><p1><sg>$ ^lose<vblex><p3><sg>$ ^two<num><m><sp>$ ^of<pr>$ ^the<det><def><pl>$ ^my<det>$ ^book<n><pl>$^.<sent>$^.<sent>$
*:abc-xyz:
I #Have #lose #two of the #my books.

==post evaluation==
*WER, PER, and other useful numbers, part 2:
*Coverage from monolingual transducer, part 2:
*Coverage from bilingual transducer, part 2:

[[Category:Sp23_StructuralTransfer]],[[Category:Sardinian]],[[Category:English]]

Sardinian and English/Structural transfer

2023-05-04T15:29:57Z

Rorlija1: /* Item 3: Posessive determiner/marker order in noun phraseology */

==pre-evaluation==
*WER, PER, and other useful numbers:
Statistics about input files
-------------------------------------------------------
Number of words in reference: 81
Number of words in test: 80
Number of unknown words (marked with a star) in test: 14
Percentage of unknown words: 17.50 %

Results when removing unknown-word marks (stars)
-------------------------------------------------------
Edit distance: 77
Word error rate (WER): 95.06 %
Number of position-independent correct words: 12
Position-independent word error rate (PER): 85.19 %
*coverage from monolingual transducer on srd.tests:
Coverage: 97.78%
Top unknown words in the corpus:
1 paìsu
1 Lettu
*coverage from bilingual transducer on srd.tests:
Number of tokenised words in the corpus: 91
Coverage: 84.62%
Top unknown words in the corpus:
2 bellu
1 paisu
1 paìsu
1 Lettu
1 furatu
1 dinari
1 punitos
1 rica
1 datu
1 milli
1 francos
1 betzu
1 iscimpru

==.rtx rules==
====Item 1: Determiners before nouns in Sardinian are omitted in English translations that do not include determiners before nouns====
*Ex: {{transferTest|srd|eng|Sa Frantza est unu paisu bellu.|France is a beautiful country.}}
*Outputs for:
*:tagger: ^Su<det><def><f><sg>$ ^Frantza<np><top><f><sg>$ ^èssere<vbser><pri><p3><sg>$ ^unu<det><ind><m><sg>$ ^paisu<n><m><sg>$ ^bellu<adj><m><sg>$^.<sent>$^.<sent>$
*:lex:
1:SELECT:0.8:Su<det><def><f><sg>:2:The<det><def><f><sg>
^Su<det><def><f><sg>/The<det><def><f><sg>$ ^Frantza<np><top><f><sg>/France<np><top><f><sg>$ ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$ ^unu<det><ind><m><sg>/a<det><ind><m><sg>$ ^paisu<n><m><sg>/country<n><sg>$ ^bellu<adj><m><sg>/beautiful<adj><m><sg>$^.<sent>/.<sent>$^.<sent>/.<sent>$
*:transfer:
Applying rule 4 (line 58): ^Su<det><def><f><sg>/The<det><def><f><sg>$ ^Frantza<np><top><f><sg>/France<np><top><f><sg>$
Applying rule 6 (line 61): ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$
Applying rule 1 (line 54): ^paisu<n><m><sg>/country<n><sg>$ ^bellu<adj><m><sg>/beautiful<adj><m><sg>$
Applying rule 3 (line 57): ^unu<det><ind><m><sg>/a<det><ind><m><sg>$ ^default<NP><PD><ND>{^paisu<n><m><sg>/country<n><sg>$ ^bellu<adj><m><sg>/beautiful<adj><m><sg>$}$
Applying rule 8 (line 64): ^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><m><sg>/a<det><ind><m><sg>$ ^default<NP><PD><ND>{^paisu<n><m><sg>/country<n><sg>$ ^bellu<adj><m><sg>/beautiful<adj><m><sg>$}$}$
Applying rule 9 (line 66): ^Default<DP><PD><ND>{^Su<det><def><f><sg>/The<det><def><f><sg>$ ^Frantza<np><top><f><sg>/France<np><top><f><sg>$}$ ^be<VP><p3><sg>{^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><m><sg>/a<det><ind><m><sg>$ ^default<NP><PD><ND>{^paisu<n><m><sg>/country<n><sg>$ ^bellu<adj><m><sg>/beautiful<adj><m><sg>$}$}$}$
Applying output rule 8 (line 66): Be<#S><p3><sg> -> ^Default<DP><PD><ND>{^Su<det><def><f><sg>/The<det><def><f><sg>$ ^Frantza<np><top><f><sg>/France<np><top><f><sg>$}$ ^be<VP><p3><sg>{^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><m><sg>/a<det><ind><m><sg>$ ^default<NP><PD><ND>{^paisu<n><m><sg>/country<n><sg>$ ^bellu<adj><m><sg>/beautiful<adj><m><sg>$}$}$}$
Applying output rule 3 (line 58): Default<DP><p3><sg> -> ^Su<det><def><f><sg>/The<det><def><f><sg>$ ^Frantza<np><top><f><sg>/France<np><top><f><sg>$
No rule specified: ^France<np><top><sg>$
Applying output rule 7 (line 64): be<VP><p3><sg> -> ^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><m><sg>/a<det><ind><m><sg>$ ^default<NP><PD><ND>{^paisu<n><m><sg>/country<n><sg>$ ^bellu<adj><m><sg>/beautiful<adj><m><sg>$}$}$
Applying output rule 5 (line 61): be<vP><p3><sg> -> ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$
No rule specified: ^be<vbser><pres><p3><sg>$
Applying output rule 2 (line 57): default<DP><p3><sg> -> ^unu<det><ind><m><sg>/a<det><ind><m><sg>$ ^default<NP><PD><ND>{^paisu<n><m><sg>/country<n><sg>$ ^bellu<adj><m><sg>/beautiful<adj><m><sg>$}$
No rule specified: ^a<det><ind><sg>$
Applying output rule 0 (line 54): default<NP><p3><sg> -> ^paisu<n><m><sg>/country<n><sg>$ ^bellu<adj><m><sg>/beautiful<adj><m><sg>$
No rule specified: ^beautiful<adj>$
No rule specified: ^country<n><sg>$
No rule specified: ^.<sent>/.<sent>$
No rule specified: ^.<sent>/.<sent>$
^France<np><top><sg>$ ^be<vbser><pres><p3><sg>$ ^a<det><ind><sg>$ ^beautiful<adj>$ ^country<n><sg>$^.<sent>$^.<sent>$
*:abc-xyz:
France is a beautiful country.

====Item 2: Noun-adjective order in noun phraseology: adjectives now come before the noun in translations when necessary:====
*Ex: {{transferTest|srd|eng|Su sardu est una limba antica.|Sardinian is an ancient language.}}
*Outputs for:
*:tagger: ^Su<det><def><m><sg>$ ^sardu<n><m><sg>$ ^èssere<vbser><pri><p3><sg>$ ^unu<det><ind><f><sg>$ ^limba<n><f><sg>$ ^anticu<adj><f><sg>$^.<sent>$^.<sent>$
*:lex:
1:SELECT:0.8:Su<det><def><m><sg>:2:The<det><def><m><sg>
^Su<det><def><m><sg>/The<det><def><m><sg>$ ^sardu<n><m><sg>/Sardinian<n><sg>$ ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$ ^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$^.<sent>/.<sent>$^.<sent>/.<sent>$
*:transfer:
No rule specified: ^Su<det><def><m><sg>/The<det><def><m><sg>$
No rule specified: ^sardu<n><m><sg>/Sardinian<n><sg>$
Applying rule 6 (line 61): ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$
Applying rule 1 (line 54): ^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$
Applying rule 3 (line 57): ^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$}$
Applying rule 8 (line 64): ^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$}$}$
Applying rule 10 (line 67): ^be<VP><p3><sg>{^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$}$}$}$
Applying output rule 9 (line 67): be<#S><p3><sg> -> ^be<VP><p3><sg>{^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$}$}$}$
No rule specified: ^prpers<prn><subj><p3><nt><sg>$
Applying output rule 7 (line 64): be<VP><p3><sg> -> ^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$}$}$
Applying output rule 5 (line 61): be<vP><p3><sg> -> ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$
No rule specified: ^be<vbser><pres><p3><sg>$
Applying output rule 2 (line 57): default<DP><p3><sg> -> ^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$}$
No rule specified: ^a<det><ind><sg>$
Applying output rule 0 (line 54): default<NP><p3><sg> -> ^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$
No rule specified: ^ancient<adj>$
No rule specified: ^language<n><sg>$
No rule specified: ^.<sent>/.<sent>$
No rule specified: ^.<sent>/.<sent>$
^The<det><def><m><sg>$ ^Sardinian<n><sg>$ ^prpers<prn><subj><p3><nt><sg>$ ^be<vbser><pres><p3><sg>$ ^a<det><ind><sg>$ ^ancient<adj>$ ^language<n><sg>$^.<sent>$^.<sent>$
*:abc-xyz:
#The Sardinian it is an ancient language.

====Item 3: Posessive determiner/marker order in noun phraseology====
*Ex: {{transferTest|srd|eng|Libru meu est.|It is my book.}}
*Outputs for:
*:tagger: ^Libru<n><m><sg>$ ^meu<adj><pos><m><sg>$ ^èssere<vbser><pri><p3><sg>$^.<sent>$^.<sent>$
*:lex: ^Libru<n><m><sg>/Book<n><sg>$ ^meu<adj><pos><m><sg>/my<det><pos><m><sg>$ ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$^.<sent>/.<sent>$^.<sent>/.<sent>$
*:transfer:
Applying rule 3 (line 58): ^Libru<n><m><sg>/Book<n><sg>$
Applying rule 1 (line 56): ^Libru<n><m><sg>/Book<n><sg>$ ^meu<adj><pos><m><sg>/my<det><pos><m><sg>$
Applying rule 6 (line 63): ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$
Applying rule 11 (line 69): ^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$
Applying rule 13 (line 72): ^Default<NP><PD><ND>{^Libru<n><m><sg>/Book<n><sg>$ ^meu<adj><pos><m><sg>/my<det><pos><m><sg>$}$ ^be<VP><p3><sg>{^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$}$
Applying output rule 12 (line 72): Be<#S><p3><sg> -> ^Default<NP><PD><ND>{^Libru<n><m><sg>/Book<n><sg>$ ^meu<adj><pos><m><sg>/my<det><pos><m><sg>$}$ ^be<VP><p3><sg>{^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$}$
Applying output rule 0 (line 56): Default<NP><p3><sg> -> ^Libru<n><m><sg>/Book<n><sg>$ ^meu<adj><pos><m><sg>/my<det><pos><m><sg>$
No rule specified: ^my<det>$
No rule specified: ^Book<n><sg>$
Applying output rule 10 (line 69): be<VP><p3><sg> -> ^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$
Applying output rule 5 (line 63): be<vP><p3><sg> -> ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$
No rule specified: ^be<vbser><pres><p3><sg>$
No rule specified: ^.<sent>/.<sent>$
No rule specified: ^.<sent>/.<sent>$
^my<det>$ ^Book<n><sg>$ ^be<vbser><pres><p3><sg>$^.<sent>$^.<sent>$
*:abc-xyz:
#my Book is.

====Item 4: For most uses/conjugations of verbs in Sardinian, the verb stands on its own without a personal pronoun, while in English personal pronouns always precede any conjugated verbs. In other words, the tags of "appo" (I have) determine a new word "I" which precedes "have" in the English translation.====
*Ex: {{transferTest|srd|eng|Appo pèrditu duos de sos libros meos.|I have lost two of my books.}}
*Outputs for:
*:tagger: ^Àere<vbhaver><pri><p1><sg>$ ^pèrdere<vblex><pp><m><sg>$ ^duos<num><m><sp>$ ^de<pr>$ ^su<det><def><m><pl>$ ^libru<n><m><pl>$ ^meu<adj><pos><m><pl>$^.<sent>$^.<sent>$
*:lex:
1:SELECT:1:de<pr>:2:of<pr>
1:SELECT:0.8:su<det><def><m><pl>:2:the<det><def><m><pl>
^Àere<vbhaver><pri><p1><sg>/Have<vbhaver><pri><p1><sg>$ ^pèrdere<vblex><pp><m><sg>/lose<vblex><pp><m><sg>$ ^duos<num><m><sp>/two<num><m><sp>$ ^de<pr>/of<pr>$ ^su<det><def><m><pl>/the<det><def><m><pl>$ ^libru<n><m><pl>/book<n><pl>$ ^meu<adj><pos><m><pl>/my<det><pos><m><pl>$^.<sent>/.<sent>$^.<sent>/.<sent>$
*:transfer:
Applying rule 7 (line 64): ^Àere<vbhaver><pri><p1><sg>/Have<vbhaver><pri><p1><sg>$
Applying rule 11 (line 69): ^Have<vP><p1><sg>{^Àere<vbhaver><pri><p1><sg>/Have<vbhaver><pri><p1><sg>$}$
Applying rule 15 (line 74): ^Have<VP><p1><sg>{^Have<vP><p1><sg>{^Àere<vbhaver><pri><p1><sg>/Have<vbhaver><pri><p1><sg>$}$}$
Applying rule 8 (line 65): ^pèrdere<vblex><pp><m><sg>/lose<vblex><pp><m><sg>$
Applying rule 10 (line 68): ^Have<vP><p1><sg>{^Àere<vbhaver><pri><p1><sg>/Have<vbhaver><pri><p1><sg>$}$ ^lose<vP><PD><sg>{^pèrdere<vblex><pp><m><sg>/lose<vblex><pp><m><sg>$}$
Applying rule 15 (line 74): ^Have<VP><p1><sg>{^Have<vP><p1><sg>{^Àere<vbhaver><pri><p1><sg>/Have<vbhaver><pri><p1><sg>$}$ ^lose<vP><PD><sg>{^pèrdere<vblex><pp><m><sg>/lose<vblex><pp><m><sg>$}$}$
Applying output rule 14 (line 74): Have<#S><p1><sg> -> ^Have<VP><p1><sg>{^Have<vP><p1><sg>{^Àere<vbhaver><pri><p1><sg>/Have<vbhaver><pri><p1><sg>$}$ ^lose<vP><PD><sg>{^pèrdere<vblex><pp><m><sg>/lose<vblex><pp><m><sg>$}$}$
No rule specified: ^prpers<prn><subj><p1><mf><sg>$
Applying output rule 9 (line 68): Have<VP><p1><sg> -> ^Have<vP><p1><sg>{^Àere<vbhaver><pri><p1><sg>/Have<vbhaver><pri><p1><sg>$}$ ^lose<vP><PD><sg>{^pèrdere<vblex><pp><m><sg>/lose<vblex><pp><m><sg>$}$
Applying output rule 6 (line 64): Have<vP><p1><sg> -> ^Àere<vbhaver><pri><p1><sg>/Have<vbhaver><pri><p1><sg>$
No rule specified: ^Have<vbhaver><pres><p1><sg>$=
Applying output rule 7 (line 65): lose<vP><p3><sg> -> ^pèrdere<vblex><pp><m><sg>/lose<vblex><pp><m><sg>$
No rule specified: ^lose<vblex><p3><sg>$
No rule specified: ^duos<num><m><sp>/two<num><m><sp>$
No rule specified: ^de<pr>/of<pr>$
Applying rule 3 (line 58): ^libru<n><m><pl>/book<n><pl>$
Applying rule 4 (line 60): ^su<det><def><m><pl>/the<det><def><m><pl>$ ^default<NP><PD><ND>{^libru<n><m><pl>/book<n><pl>$}$
Applying rule 1 (line 56): ^libru<n><m><pl>/book<n><pl>$ ^meu<adj><pos><m><pl>/my<det><pos><m><pl>$
Applying rule 4 (line 60): ^su<det><def><m><pl>/the<det><def><m><pl>$ ^default<NP><PD><ND>{^libru<n><m><pl>/book<n><pl>$ ^meu<adj><pos><m><pl>/my<det><pos><m><pl>$}$
Applying output rule 3 (line 60): default<DP><PD><ND> -> ^su<det><def><m><pl>/the<det><def><m><pl>$ ^default<NP><PD><ND>{^libru<n><m><pl>/book<n><pl>$ ^meu<adj><pos><m><pl>/my<det><pos><m><pl>$}$
No rule specified: ^the<det><def><pl>$
Applying output rule 0 (line 56): default<NP><p3><sg> -> ^libru<n><m><pl>/book<n><pl>$ ^meu<adj><pos><m><pl>/my<det><pos><m><pl>$
No rule specified: ^my<det>$
No rule specified: ^book<n><pl>$
No rule specified: ^.<sent>/.<sent>$
No rule specified: ^.<sent>/.<sent>$
^prpers<prn><subj><p1><mf><sg>$ ^Have<vbhaver><pres><p1><sg>$ ^lose<vblex><p3><sg>$ ^two<num><m><sp>$ ^of<pr>$ ^the<det><def><pl>$ ^my<det>$ ^book<n><pl>$^.<sent>$^.<sent>$
*:abc-xyz:
I #Have #lose #two of the #my books.

==post evaluation==
*WER, PER, and other useful numbers, part 2:
*Coverage from monolingual transducer, part 2:
*Coverage from bilingual transducer, part 2:

[[Category:Sp23_StructuralTransfer]],[[Category:Sardinian]],[[Category:English]]

Sardinian and English/Structural transfer

2023-05-04T15:29:42Z

Rorlija1: /* Item 3: Posessive determiner/marker order in noun phraseology */

==pre-evaluation==
*WER, PER, and other useful numbers:
Statistics about input files
-------------------------------------------------------
Number of words in reference: 81
Number of words in test: 80
Number of unknown words (marked with a star) in test: 14
Percentage of unknown words: 17.50 %

Results when removing unknown-word marks (stars)
-------------------------------------------------------
Edit distance: 77
Word error rate (WER): 95.06 %
Number of position-independent correct words: 12
Position-independent word error rate (PER): 85.19 %
*coverage from monolingual transducer on srd.tests:
Coverage: 97.78%
Top unknown words in the corpus:
1 paìsu
1 Lettu
*coverage from bilingual transducer on srd.tests:
Number of tokenised words in the corpus: 91
Coverage: 84.62%
Top unknown words in the corpus:
2 bellu
1 paisu
1 paìsu
1 Lettu
1 furatu
1 dinari
1 punitos
1 rica
1 datu
1 milli
1 francos
1 betzu
1 iscimpru

==.rtx rules==
====Item 1: Determiners before nouns in Sardinian are omitted in English translations that do not include determiners before nouns====
*Ex: {{transferTest|srd|eng|Sa Frantza est unu paisu bellu.|France is a beautiful country.}}
*Outputs for:
*:tagger: ^Su<det><def><f><sg>$ ^Frantza<np><top><f><sg>$ ^èssere<vbser><pri><p3><sg>$ ^unu<det><ind><m><sg>$ ^paisu<n><m><sg>$ ^bellu<adj><m><sg>$^.<sent>$^.<sent>$
*:lex:
1:SELECT:0.8:Su<det><def><f><sg>:2:The<det><def><f><sg>
^Su<det><def><f><sg>/The<det><def><f><sg>$ ^Frantza<np><top><f><sg>/France<np><top><f><sg>$ ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$ ^unu<det><ind><m><sg>/a<det><ind><m><sg>$ ^paisu<n><m><sg>/country<n><sg>$ ^bellu<adj><m><sg>/beautiful<adj><m><sg>$^.<sent>/.<sent>$^.<sent>/.<sent>$
*:transfer:
Applying rule 4 (line 58): ^Su<det><def><f><sg>/The<det><def><f><sg>$ ^Frantza<np><top><f><sg>/France<np><top><f><sg>$
Applying rule 6 (line 61): ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$
Applying rule 1 (line 54): ^paisu<n><m><sg>/country<n><sg>$ ^bellu<adj><m><sg>/beautiful<adj><m><sg>$
Applying rule 3 (line 57): ^unu<det><ind><m><sg>/a<det><ind><m><sg>$ ^default<NP><PD><ND>{^paisu<n><m><sg>/country<n><sg>$ ^bellu<adj><m><sg>/beautiful<adj><m><sg>$}$
Applying rule 8 (line 64): ^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><m><sg>/a<det><ind><m><sg>$ ^default<NP><PD><ND>{^paisu<n><m><sg>/country<n><sg>$ ^bellu<adj><m><sg>/beautiful<adj><m><sg>$}$}$
Applying rule 9 (line 66): ^Default<DP><PD><ND>{^Su<det><def><f><sg>/The<det><def><f><sg>$ ^Frantza<np><top><f><sg>/France<np><top><f><sg>$}$ ^be<VP><p3><sg>{^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><m><sg>/a<det><ind><m><sg>$ ^default<NP><PD><ND>{^paisu<n><m><sg>/country<n><sg>$ ^bellu<adj><m><sg>/beautiful<adj><m><sg>$}$}$}$
Applying output rule 8 (line 66): Be<#S><p3><sg> -> ^Default<DP><PD><ND>{^Su<det><def><f><sg>/The<det><def><f><sg>$ ^Frantza<np><top><f><sg>/France<np><top><f><sg>$}$ ^be<VP><p3><sg>{^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><m><sg>/a<det><ind><m><sg>$ ^default<NP><PD><ND>{^paisu<n><m><sg>/country<n><sg>$ ^bellu<adj><m><sg>/beautiful<adj><m><sg>$}$}$}$
Applying output rule 3 (line 58): Default<DP><p3><sg> -> ^Su<det><def><f><sg>/The<det><def><f><sg>$ ^Frantza<np><top><f><sg>/France<np><top><f><sg>$
No rule specified: ^France<np><top><sg>$
Applying output rule 7 (line 64): be<VP><p3><sg> -> ^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><m><sg>/a<det><ind><m><sg>$ ^default<NP><PD><ND>{^paisu<n><m><sg>/country<n><sg>$ ^bellu<adj><m><sg>/beautiful<adj><m><sg>$}$}$
Applying output rule 5 (line 61): be<vP><p3><sg> -> ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$
No rule specified: ^be<vbser><pres><p3><sg>$
Applying output rule 2 (line 57): default<DP><p3><sg> -> ^unu<det><ind><m><sg>/a<det><ind><m><sg>$ ^default<NP><PD><ND>{^paisu<n><m><sg>/country<n><sg>$ ^bellu<adj><m><sg>/beautiful<adj><m><sg>$}$
No rule specified: ^a<det><ind><sg>$
Applying output rule 0 (line 54): default<NP><p3><sg> -> ^paisu<n><m><sg>/country<n><sg>$ ^bellu<adj><m><sg>/beautiful<adj><m><sg>$
No rule specified: ^beautiful<adj>$
No rule specified: ^country<n><sg>$
No rule specified: ^.<sent>/.<sent>$
No rule specified: ^.<sent>/.<sent>$
^France<np><top><sg>$ ^be<vbser><pres><p3><sg>$ ^a<det><ind><sg>$ ^beautiful<adj>$ ^country<n><sg>$^.<sent>$^.<sent>$
*:abc-xyz:
France is a beautiful country.

====Item 2: Noun-adjective order in noun phraseology: adjectives now come before the noun in translations when necessary:====
*Ex: {{transferTest|srd|eng|Su sardu est una limba antica.|Sardinian is an ancient language.}}
*Outputs for:
*:tagger: ^Su<det><def><m><sg>$ ^sardu<n><m><sg>$ ^èssere<vbser><pri><p3><sg>$ ^unu<det><ind><f><sg>$ ^limba<n><f><sg>$ ^anticu<adj><f><sg>$^.<sent>$^.<sent>$
*:lex:
1:SELECT:0.8:Su<det><def><m><sg>:2:The<det><def><m><sg>
^Su<det><def><m><sg>/The<det><def><m><sg>$ ^sardu<n><m><sg>/Sardinian<n><sg>$ ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$ ^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$^.<sent>/.<sent>$^.<sent>/.<sent>$
*:transfer:
No rule specified: ^Su<det><def><m><sg>/The<det><def><m><sg>$
No rule specified: ^sardu<n><m><sg>/Sardinian<n><sg>$
Applying rule 6 (line 61): ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$
Applying rule 1 (line 54): ^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$
Applying rule 3 (line 57): ^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$}$
Applying rule 8 (line 64): ^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$}$}$
Applying rule 10 (line 67): ^be<VP><p3><sg>{^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$}$}$}$
Applying output rule 9 (line 67): be<#S><p3><sg> -> ^be<VP><p3><sg>{^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$}$}$}$
No rule specified: ^prpers<prn><subj><p3><nt><sg>$
Applying output rule 7 (line 64): be<VP><p3><sg> -> ^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$}$}$
Applying output rule 5 (line 61): be<vP><p3><sg> -> ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$
No rule specified: ^be<vbser><pres><p3><sg>$
Applying output rule 2 (line 57): default<DP><p3><sg> -> ^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$}$
No rule specified: ^a<det><ind><sg>$
Applying output rule 0 (line 54): default<NP><p3><sg> -> ^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$
No rule specified: ^ancient<adj>$
No rule specified: ^language<n><sg>$
No rule specified: ^.<sent>/.<sent>$
No rule specified: ^.<sent>/.<sent>$
^The<det><def><m><sg>$ ^Sardinian<n><sg>$ ^prpers<prn><subj><p3><nt><sg>$ ^be<vbser><pres><p3><sg>$ ^a<det><ind><sg>$ ^ancient<adj>$ ^language<n><sg>$^.<sent>$^.<sent>$
*:abc-xyz:
#The Sardinian it is an ancient language.

====Item 3: Posessive determiner/marker order in noun phraseology====
*Ex: {{transferTest|srd|eng|Libru meu est.|It is my book.}}
*Outputs for:
*:tagger: ^Libru<n><m><sg>$ ^meu<adj><pos><m><sg>$ ^èssere<vbser><pri><p3><sg>$^.<sent>$^.<sent>$
*:lex: ^Libru<n><m><sg>/Book<n><sg>$ ^meu<adj><pos><m><sg>/my<det><pos><m><sg>$ ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$^.<sent>/.<sent>$^.<sent>/.<sent>$
*:transfer:
Applying rule 3 (line 58): ^Libru<n><m><sg>/Book<n><sg>$
Applying rule 1 (line 56): ^Libru<n><m><sg>/Book<n><sg>$ ^meu<adj><pos><m><sg>/my<det><pos><m><sg>$
Applying rule 6 (line 63): ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$
Applying rule 11 (line 69): ^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$
Applying rule 13 (line 72): ^Default<NP><PD><ND>{^Libru<n><m><sg>/Book<n><sg>$ ^meu<adj><pos><m><sg>/my<det><pos><m><sg>$}$ ^be<VP><p3><sg>{^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$}$
Applying output rule 12 (line 72): Be<S><p3><sg> -> ^Default<NP><PD><ND>{^Libru<n><m><sg>/Book<n><sg>$ ^meu<adj><pos><m><sg>/my<det><pos><m><sg>$}$ ^be<VP><p3><sg>{^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$}$
Applying output rule 0 (line 56): Default<NP><p3><sg> -> ^Libru<n><m><sg>/Book<n><sg>$ ^meu<adj><pos><m><sg>/my<det><pos><m><sg>$
No rule specified: ^my<det>$
No rule specified: ^Book<n><sg>$
Applying output rule 10 (line 69): be<VP><p3><sg> -> ^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$
Applying output rule 5 (line 63): be<vP><p3><sg> -> ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$
No rule specified: ^be<vbser><pres><p3><sg>$
No rule specified: ^.<sent>/.<sent>$
No rule specified: ^.<sent>/.<sent>$
^my<det>$ ^Book<n><sg>$ ^be<vbser><pres><p3><sg>$^.<sent>$^.<sent>$
*:abc-xyz:
#my Book is.

====Item 4: For most uses/conjugations of verbs in Sardinian, the verb stands on its own without a personal pronoun, while in English personal pronouns always precede any conjugated verbs. In other words, the tags of "appo" (I have) determine a new word "I" which precedes "have" in the English translation.====
*Ex: {{transferTest|srd|eng|Appo pèrditu duos de sos libros meos.|I have lost two of my books.}}
*Outputs for:
*:tagger: ^Àere<vbhaver><pri><p1><sg>$ ^pèrdere<vblex><pp><m><sg>$ ^duos<num><m><sp>$ ^de<pr>$ ^su<det><def><m><pl>$ ^libru<n><m><pl>$ ^meu<adj><pos><m><pl>$^.<sent>$^.<sent>$
*:lex:
1:SELECT:1:de<pr>:2:of<pr>
1:SELECT:0.8:su<det><def><m><pl>:2:the<det><def><m><pl>
^Àere<vbhaver><pri><p1><sg>/Have<vbhaver><pri><p1><sg>$ ^pèrdere<vblex><pp><m><sg>/lose<vblex><pp><m><sg>$ ^duos<num><m><sp>/two<num><m><sp>$ ^de<pr>/of<pr>$ ^su<det><def><m><pl>/the<det><def><m><pl>$ ^libru<n><m><pl>/book<n><pl>$ ^meu<adj><pos><m><pl>/my<det><pos><m><pl>$^.<sent>/.<sent>$^.<sent>/.<sent>$
*:transfer:
Applying rule 7 (line 64): ^Àere<vbhaver><pri><p1><sg>/Have<vbhaver><pri><p1><sg>$
Applying rule 11 (line 69): ^Have<vP><p1><sg>{^Àere<vbhaver><pri><p1><sg>/Have<vbhaver><pri><p1><sg>$}$
Applying rule 15 (line 74): ^Have<VP><p1><sg>{^Have<vP><p1><sg>{^Àere<vbhaver><pri><p1><sg>/Have<vbhaver><pri><p1><sg>$}$}$
Applying rule 8 (line 65): ^pèrdere<vblex><pp><m><sg>/lose<vblex><pp><m><sg>$
Applying rule 10 (line 68): ^Have<vP><p1><sg>{^Àere<vbhaver><pri><p1><sg>/Have<vbhaver><pri><p1><sg>$}$ ^lose<vP><PD><sg>{^pèrdere<vblex><pp><m><sg>/lose<vblex><pp><m><sg>$}$
Applying rule 15 (line 74): ^Have<VP><p1><sg>{^Have<vP><p1><sg>{^Àere<vbhaver><pri><p1><sg>/Have<vbhaver><pri><p1><sg>$}$ ^lose<vP><PD><sg>{^pèrdere<vblex><pp><m><sg>/lose<vblex><pp><m><sg>$}$}$
Applying output rule 14 (line 74): Have<#S><p1><sg> -> ^Have<VP><p1><sg>{^Have<vP><p1><sg>{^Àere<vbhaver><pri><p1><sg>/Have<vbhaver><pri><p1><sg>$}$ ^lose<vP><PD><sg>{^pèrdere<vblex><pp><m><sg>/lose<vblex><pp><m><sg>$}$}$
No rule specified: ^prpers<prn><subj><p1><mf><sg>$
Applying output rule 9 (line 68): Have<VP><p1><sg> -> ^Have<vP><p1><sg>{^Àere<vbhaver><pri><p1><sg>/Have<vbhaver><pri><p1><sg>$}$ ^lose<vP><PD><sg>{^pèrdere<vblex><pp><m><sg>/lose<vblex><pp><m><sg>$}$
Applying output rule 6 (line 64): Have<vP><p1><sg> -> ^Àere<vbhaver><pri><p1><sg>/Have<vbhaver><pri><p1><sg>$
No rule specified: ^Have<vbhaver><pres><p1><sg>$=
Applying output rule 7 (line 65): lose<vP><p3><sg> -> ^pèrdere<vblex><pp><m><sg>/lose<vblex><pp><m><sg>$
No rule specified: ^lose<vblex><p3><sg>$
No rule specified: ^duos<num><m><sp>/two<num><m><sp>$
No rule specified: ^de<pr>/of<pr>$
Applying rule 3 (line 58): ^libru<n><m><pl>/book<n><pl>$
Applying rule 4 (line 60): ^su<det><def><m><pl>/the<det><def><m><pl>$ ^default<NP><PD><ND>{^libru<n><m><pl>/book<n><pl>$}$
Applying rule 1 (line 56): ^libru<n><m><pl>/book<n><pl>$ ^meu<adj><pos><m><pl>/my<det><pos><m><pl>$
Applying rule 4 (line 60): ^su<det><def><m><pl>/the<det><def><m><pl>$ ^default<NP><PD><ND>{^libru<n><m><pl>/book<n><pl>$ ^meu<adj><pos><m><pl>/my<det><pos><m><pl>$}$
Applying output rule 3 (line 60): default<DP><PD><ND> -> ^su<det><def><m><pl>/the<det><def><m><pl>$ ^default<NP><PD><ND>{^libru<n><m><pl>/book<n><pl>$ ^meu<adj><pos><m><pl>/my<det><pos><m><pl>$}$
No rule specified: ^the<det><def><pl>$
Applying output rule 0 (line 56): default<NP><p3><sg> -> ^libru<n><m><pl>/book<n><pl>$ ^meu<adj><pos><m><pl>/my<det><pos><m><pl>$
No rule specified: ^my<det>$
No rule specified: ^book<n><pl>$
No rule specified: ^.<sent>/.<sent>$
No rule specified: ^.<sent>/.<sent>$
^prpers<prn><subj><p1><mf><sg>$ ^Have<vbhaver><pres><p1><sg>$ ^lose<vblex><p3><sg>$ ^two<num><m><sp>$ ^of<pr>$ ^the<det><def><pl>$ ^my<det>$ ^book<n><pl>$^.<sent>$^.<sent>$
*:abc-xyz:
I #Have #lose #two of the #my books.

==post evaluation==
*WER, PER, and other useful numbers, part 2:
*Coverage from monolingual transducer, part 2:
*Coverage from bilingual transducer, part 2:

[[Category:Sp23_StructuralTransfer]],[[Category:Sardinian]],[[Category:English]]

Sardinian and English/Structural transfer

2023-05-04T15:26:32Z

==pre-evaluation==
*WER, PER, and other useful numbers:
Statistics about input files
-------------------------------------------------------
Number of words in reference: 81
Number of words in test: 80
Number of unknown words (marked with a star) in test: 14
Percentage of unknown words: 17.50 %

Results when removing unknown-word marks (stars)
-------------------------------------------------------
Edit distance: 77
Word error rate (WER): 95.06 %
Number of position-independent correct words: 12
Position-independent word error rate (PER): 85.19 %
*coverage from monolingual transducer on srd.tests:
Coverage: 97.78%
Top unknown words in the corpus:
1 paìsu
1 Lettu
*coverage from bilingual transducer on srd.tests:
Number of tokenised words in the corpus: 91
Coverage: 84.62%
Top unknown words in the corpus:
2 bellu
1 paisu
1 paìsu
1 Lettu
1 furatu
1 dinari
1 punitos
1 rica
1 datu
1 milli
1 francos
1 betzu
1 iscimpru

==.rtx rules==
====Item 1: Determiners before nouns in Sardinian are omitted in English translations that do not include determiners before nouns====
*Ex: {{transferTest|srd|eng|Sa Frantza est unu paisu bellu.|France is a beautiful country.}}
*Outputs for:
*:tagger: ^Su<det><def><f><sg>$ ^Frantza<np><top><f><sg>$ ^èssere<vbser><pri><p3><sg>$ ^unu<det><ind><m><sg>$ ^paisu<n><m><sg>$ ^bellu<adj><m><sg>$^.<sent>$^.<sent>$
*:lex:
1:SELECT:0.8:Su<det><def><f><sg>:2:The<det><def><f><sg>
^Su<det><def><f><sg>/The<det><def><f><sg>$ ^Frantza<np><top><f><sg>/France<np><top><f><sg>$ ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$ ^unu<det><ind><m><sg>/a<det><ind><m><sg>$ ^paisu<n><m><sg>/country<n><sg>$ ^bellu<adj><m><sg>/beautiful<adj><m><sg>$^.<sent>/.<sent>$^.<sent>/.<sent>$
*:transfer:
Applying rule 4 (line 58): ^Su<det><def><f><sg>/The<det><def><f><sg>$ ^Frantza<np><top><f><sg>/France<np><top><f><sg>$
Applying rule 6 (line 61): ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$
Applying rule 1 (line 54): ^paisu<n><m><sg>/country<n><sg>$ ^bellu<adj><m><sg>/beautiful<adj><m><sg>$
Applying rule 3 (line 57): ^unu<det><ind><m><sg>/a<det><ind><m><sg>$ ^default<NP><PD><ND>{^paisu<n><m><sg>/country<n><sg>$ ^bellu<adj><m><sg>/beautiful<adj><m><sg>$}$
Applying rule 8 (line 64): ^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><m><sg>/a<det><ind><m><sg>$ ^default<NP><PD><ND>{^paisu<n><m><sg>/country<n><sg>$ ^bellu<adj><m><sg>/beautiful<adj><m><sg>$}$}$
Applying rule 9 (line 66): ^Default<DP><PD><ND>{^Su<det><def><f><sg>/The<det><def><f><sg>$ ^Frantza<np><top><f><sg>/France<np><top><f><sg>$}$ ^be<VP><p3><sg>{^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><m><sg>/a<det><ind><m><sg>$ ^default<NP><PD><ND>{^paisu<n><m><sg>/country<n><sg>$ ^bellu<adj><m><sg>/beautiful<adj><m><sg>$}$}$}$
Applying output rule 8 (line 66): Be<#S><p3><sg> -> ^Default<DP><PD><ND>{^Su<det><def><f><sg>/The<det><def><f><sg>$ ^Frantza<np><top><f><sg>/France<np><top><f><sg>$}$ ^be<VP><p3><sg>{^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><m><sg>/a<det><ind><m><sg>$ ^default<NP><PD><ND>{^paisu<n><m><sg>/country<n><sg>$ ^bellu<adj><m><sg>/beautiful<adj><m><sg>$}$}$}$
Applying output rule 3 (line 58): Default<DP><p3><sg> -> ^Su<det><def><f><sg>/The<det><def><f><sg>$ ^Frantza<np><top><f><sg>/France<np><top><f><sg>$
No rule specified: ^France<np><top><sg>$
Applying output rule 7 (line 64): be<VP><p3><sg> -> ^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><m><sg>/a<det><ind><m><sg>$ ^default<NP><PD><ND>{^paisu<n><m><sg>/country<n><sg>$ ^bellu<adj><m><sg>/beautiful<adj><m><sg>$}$}$
Applying output rule 5 (line 61): be<vP><p3><sg> -> ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$
No rule specified: ^be<vbser><pres><p3><sg>$
Applying output rule 2 (line 57): default<DP><p3><sg> -> ^unu<det><ind><m><sg>/a<det><ind><m><sg>$ ^default<NP><PD><ND>{^paisu<n><m><sg>/country<n><sg>$ ^bellu<adj><m><sg>/beautiful<adj><m><sg>$}$
No rule specified: ^a<det><ind><sg>$
Applying output rule 0 (line 54): default<NP><p3><sg> -> ^paisu<n><m><sg>/country<n><sg>$ ^bellu<adj><m><sg>/beautiful<adj><m><sg>$
No rule specified: ^beautiful<adj>$
No rule specified: ^country<n><sg>$
No rule specified: ^.<sent>/.<sent>$
No rule specified: ^.<sent>/.<sent>$
^France<np><top><sg>$ ^be<vbser><pres><p3><sg>$ ^a<det><ind><sg>$ ^beautiful<adj>$ ^country<n><sg>$^.<sent>$^.<sent>$
*:abc-xyz:
France is a beautiful country.

====Item 2: Noun-adjective order in noun phraseology: adjectives now come before the noun in translations when necessary:====
*Ex: {{transferTest|srd|eng|Su sardu est una limba antica.|Sardinian is an ancient language.}}
*Outputs for:
*:tagger: ^Su<det><def><m><sg>$ ^sardu<n><m><sg>$ ^èssere<vbser><pri><p3><sg>$ ^unu<det><ind><f><sg>$ ^limba<n><f><sg>$ ^anticu<adj><f><sg>$^.<sent>$^.<sent>$
*:lex:
1:SELECT:0.8:Su<det><def><m><sg>:2:The<det><def><m><sg>
^Su<det><def><m><sg>/The<det><def><m><sg>$ ^sardu<n><m><sg>/Sardinian<n><sg>$ ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$ ^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$^.<sent>/.<sent>$^.<sent>/.<sent>$
*:transfer:
No rule specified: ^Su<det><def><m><sg>/The<det><def><m><sg>$
No rule specified: ^sardu<n><m><sg>/Sardinian<n><sg>$
Applying rule 6 (line 61): ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$
Applying rule 1 (line 54): ^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$
Applying rule 3 (line 57): ^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$}$
Applying rule 8 (line 64): ^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$}$}$
Applying rule 10 (line 67): ^be<VP><p3><sg>{^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$}$}$}$
Applying output rule 9 (line 67): be<#S><p3><sg> -> ^be<VP><p3><sg>{^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$}$}$}$
No rule specified: ^prpers<prn><subj><p3><nt><sg>$
Applying output rule 7 (line 64): be<VP><p3><sg> -> ^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$}$}$
Applying output rule 5 (line 61): be<vP><p3><sg> -> ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$
No rule specified: ^be<vbser><pres><p3><sg>$
Applying output rule 2 (line 57): default<DP><p3><sg> -> ^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$}$
No rule specified: ^a<det><ind><sg>$
Applying output rule 0 (line 54): default<NP><p3><sg> -> ^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$
No rule specified: ^ancient<adj>$
No rule specified: ^language<n><sg>$
No rule specified: ^.<sent>/.<sent>$
No rule specified: ^.<sent>/.<sent>$
^The<det><def><m><sg>$ ^Sardinian<n><sg>$ ^prpers<prn><subj><p3><nt><sg>$ ^be<vbser><pres><p3><sg>$ ^a<det><ind><sg>$ ^ancient<adj>$ ^language<n><sg>$^.<sent>$^.<sent>$
*:abc-xyz:
#The Sardinian it is an ancient language.

====Item 3: Posessive determiner/marker order in noun phraseology====
*Ex: {{transferTest|srd|eng|Libru meu est.|It is my book.}}
*Outputs for:
*:tagger: ^Libru<n><m><sg>$ ^meu<adj><pos><m><sg>$ ^èssere<vbser><pri><p3><sg>$^.<sent>$^.<sent>$
*:lex: ^Libru<n><m><sg>/Book<n><sg>$ ^meu<adj><pos><m><sg>/my<det><pos><m><sg>$ ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$^.<sent>/.<sent>$^.<sent>/.<sent>$
*:transfer:
Applying rule 1 (line 54): ^Libru<n><m><sg>/Book<n><sg>$ ^meu<adj><pos><m><sg>/my<det><pos><m><sg>$
Applying output rule 0 (line 54): Default<NP><PD><ND> -> ^Libru<n><m><sg>/Book<n><sg>$ ^meu<adj><pos><m><sg>/my<det><pos><m><sg>$
No rule specified: ^my<det>$
No rule specified: ^Book<n><sg>$
Applying rule 6 (line 61): ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$
Applying output rule 5 (line 61): be<vP><p3><sg> -> ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$
No rule specified: ^be<vbser><pres><p3><sg>$
No rule specified: ^.<sent>/.<sent>$
No rule specified: ^.<sent>/.<sent>$
^my<det>$ ^Book<n><sg>$ ^be<vbser><pres><p3><sg>$^.<sent>$^.<sent>$
*:abc-xyz:
#my Book is.

====Item 4: For most uses/conjugations of verbs in Sardinian, the verb stands on its own without a personal pronoun, while in English personal pronouns always precede any conjugated verbs. In other words, the tags of "appo" (I have) determine a new word "I" which precedes "have" in the English translation.====
*Ex: {{transferTest|srd|eng|Appo pèrditu duos de sos libros meos.|I have lost two of my books.}}
*Outputs for:
*:tagger: ^Àere<vbhaver><pri><p1><sg>$ ^pèrdere<vblex><pp><m><sg>$ ^duos<num><m><sp>$ ^de<pr>$ ^su<det><def><m><pl>$ ^libru<n><m><pl>$ ^meu<adj><pos><m><pl>$^.<sent>$^.<sent>$
*:lex:
1:SELECT:1:de<pr>:2:of<pr>
1:SELECT:0.8:su<det><def><m><pl>:2:the<det><def><m><pl>
^Àere<vbhaver><pri><p1><sg>/Have<vbhaver><pri><p1><sg>$ ^pèrdere<vblex><pp><m><sg>/lose<vblex><pp><m><sg>$ ^duos<num><m><sp>/two<num><m><sp>$ ^de<pr>/of<pr>$ ^su<det><def><m><pl>/the<det><def><m><pl>$ ^libru<n><m><pl>/book<n><pl>$ ^meu<adj><pos><m><pl>/my<det><pos><m><pl>$^.<sent>/.<sent>$^.<sent>/.<sent>$
*:transfer:
Applying rule 7 (line 64): ^Àere<vbhaver><pri><p1><sg>/Have<vbhaver><pri><p1><sg>$
Applying rule 11 (line 69): ^Have<vP><p1><sg>{^Àere<vbhaver><pri><p1><sg>/Have<vbhaver><pri><p1><sg>$}$
Applying rule 15 (line 74): ^Have<VP><p1><sg>{^Have<vP><p1><sg>{^Àere<vbhaver><pri><p1><sg>/Have<vbhaver><pri><p1><sg>$}$}$
Applying rule 8 (line 65): ^pèrdere<vblex><pp><m><sg>/lose<vblex><pp><m><sg>$
Applying rule 10 (line 68): ^Have<vP><p1><sg>{^Àere<vbhaver><pri><p1><sg>/Have<vbhaver><pri><p1><sg>$}$ ^lose<vP><PD><sg>{^pèrdere<vblex><pp><m><sg>/lose<vblex><pp><m><sg>$}$
Applying rule 15 (line 74): ^Have<VP><p1><sg>{^Have<vP><p1><sg>{^Àere<vbhaver><pri><p1><sg>/Have<vbhaver><pri><p1><sg>$}$ ^lose<vP><PD><sg>{^pèrdere<vblex><pp><m><sg>/lose<vblex><pp><m><sg>$}$}$
Applying output rule 14 (line 74): Have<#S><p1><sg> -> ^Have<VP><p1><sg>{^Have<vP><p1><sg>{^Àere<vbhaver><pri><p1><sg>/Have<vbhaver><pri><p1><sg>$}$ ^lose<vP><PD><sg>{^pèrdere<vblex><pp><m><sg>/lose<vblex><pp><m><sg>$}$}$
No rule specified: ^prpers<prn><subj><p1><mf><sg>$
Applying output rule 9 (line 68): Have<VP><p1><sg> -> ^Have<vP><p1><sg>{^Àere<vbhaver><pri><p1><sg>/Have<vbhaver><pri><p1><sg>$}$ ^lose<vP><PD><sg>{^pèrdere<vblex><pp><m><sg>/lose<vblex><pp><m><sg>$}$
Applying output rule 6 (line 64): Have<vP><p1><sg> -> ^Àere<vbhaver><pri><p1><sg>/Have<vbhaver><pri><p1><sg>$
No rule specified: ^Have<vbhaver><pres><p1><sg>$=
Applying output rule 7 (line 65): lose<vP><p3><sg> -> ^pèrdere<vblex><pp><m><sg>/lose<vblex><pp><m><sg>$
No rule specified: ^lose<vblex><p3><sg>$
No rule specified: ^duos<num><m><sp>/two<num><m><sp>$
No rule specified: ^de<pr>/of<pr>$
Applying rule 3 (line 58): ^libru<n><m><pl>/book<n><pl>$
Applying rule 4 (line 60): ^su<det><def><m><pl>/the<det><def><m><pl>$ ^default<NP><PD><ND>{^libru<n><m><pl>/book<n><pl>$}$
Applying rule 1 (line 56): ^libru<n><m><pl>/book<n><pl>$ ^meu<adj><pos><m><pl>/my<det><pos><m><pl>$
Applying rule 4 (line 60): ^su<det><def><m><pl>/the<det><def><m><pl>$ ^default<NP><PD><ND>{^libru<n><m><pl>/book<n><pl>$ ^meu<adj><pos><m><pl>/my<det><pos><m><pl>$}$
Applying output rule 3 (line 60): default<DP><PD><ND> -> ^su<det><def><m><pl>/the<det><def><m><pl>$ ^default<NP><PD><ND>{^libru<n><m><pl>/book<n><pl>$ ^meu<adj><pos><m><pl>/my<det><pos><m><pl>$}$
No rule specified: ^the<det><def><pl>$
Applying output rule 0 (line 56): default<NP><p3><sg> -> ^libru<n><m><pl>/book<n><pl>$ ^meu<adj><pos><m><pl>/my<det><pos><m><pl>$
No rule specified: ^my<det>$
No rule specified: ^book<n><pl>$
No rule specified: ^.<sent>/.<sent>$
No rule specified: ^.<sent>/.<sent>$
^prpers<prn><subj><p1><mf><sg>$ ^Have<vbhaver><pres><p1><sg>$ ^lose<vblex><p3><sg>$ ^two<num><m><sp>$ ^of<pr>$ ^the<det><def><pl>$ ^my<det>$ ^book<n><pl>$^.<sent>$^.<sent>$
*:abc-xyz:
I #Have #lose #two of the #my books.

==post evaluation==
*WER, PER, and other useful numbers, part 2:
*Coverage from monolingual transducer, part 2:
*Coverage from bilingual transducer, part 2:

[[Category:Sp23_StructuralTransfer]],[[Category:Sardinian]],[[Category:English]]

Sardinian and English/Lexical selection

2023-05-03T20:04:12Z

Rorlija1: /* srd → eng */

==srd → eng==
*Cases of a one-to-many translation and sentences where the meaning is unambiguous:
:*Rule #1: "pro" in Sardinian can be translated as both "for" and "to":
::'''Pro''' bider s'artìculu sighire custu culligamentu. → '''To''' read the article click on this link.
::'''Pro''' su libru meu mandico sa pasta kin casu. → '''For''' my book I ate pasta with cheese.
:*Rule #2: "de" translates to "to" and "of":
::Custu artìculu chircat '''de''' bogare a pizu sos ammentos documentados de cando si tenzeint sas primas disputas tra poetes a bolu e cale esserent sas règulas de su cunfrontu. → The article tries '''to''' shed light on the period to which the first testimonies of competitions between improvising poets date back and the modalities that characterized the confrontation.
::Appo pèrditu duos '''de''' sos libros meos → I have lost two '''of''' my books

*Generalizations:
:*Rule #1: when "pro" is followed by a verb, we should have the mapping "pro → to"
:*Rule #2: when "de" preceded by a number, we should have the mapping "de → of"
::(When these rules don't apply, the translations "pro → for" and "de → to" are used.)

*'''Second extra lrx rule (for polished RBMT lab)'''
:*"a" in Sardinian can be translated to both "to" and "at" in English
::Ex: "'''a''' sas nove" → "'''at''' nine [o'clock]"
::Ex2: "Sun andatos '''a''' Frantza." → "They went '''to''' France."
::So, we opted to translate "a" to "to" in general usage but to translate "a" to "at" when it occurs in a time-telling phrase (i.e. when followed by a determiner (the) and a number).

*'''Third extra lrx rule (for polished RBMT lab)'''
:*To tell the time in Sardinian, one says "a sas nove" (the nine) and not "at nine [o'clock]" (see sentences corpus for example)
::So, we opted to translate "su" (the) as "[null]" when followed by a number and preceded by "a", to translate "su" as (the) when followed by a noun modified by optional adjectives and preceded by "a," and to translate "su" as (the) when followed by a noun but not necessarily preceded by "a."

*'''We also added a rule that ensures "est" translates to "is" and not "east."'''

[[Category:Sp23_LexicalSelection]],[[Category:Sardinian]],[[Category:English]]

Sardinian and English/Structural transfer

2023-05-03T19:54:13Z

==pre-evaluation==
*WER, PER, and other useful numbers:
Statistics about input files
-------------------------------------------------------
Number of words in reference: 81
Number of words in test: 80
Number of unknown words (marked with a star) in test: 14
Percentage of unknown words: 17.50 %

Results when removing unknown-word marks (stars)
-------------------------------------------------------
Edit distance: 77
Word error rate (WER): 95.06 %
Number of position-independent correct words: 12
Position-independent word error rate (PER): 85.19 %
*coverage from monolingual transducer on srd.tests:
Coverage: 97.78%
Top unknown words in the corpus:
1 paìsu
1 Lettu
*coverage from bilingual transducer on srd.tests:
Number of tokenised words in the corpus: 91
Coverage: 84.62%
Top unknown words in the corpus:
2 bellu
1 paisu
1 paìsu
1 Lettu
1 furatu
1 dinari
1 punitos
1 rica
1 datu
1 milli
1 francos
1 betzu
1 iscimpru

==.rtx rules==
====Item 1: Determiners before nouns in Sardinian are omitted in English translations that do not include determiners before nouns====
*Ex: {{transferTest|srd|eng|Sa Frantza est unu paisu bellu.|France is a beautiful country.}}
*Outputs for:
*:tagger: ^Su<det><def><f><sg>$ ^Frantza<np><top><f><sg>$ ^èssere<vbser><pri><p3><sg>$ ^unu<det><ind><m><sg>$ ^paisu<n><m><sg>$ ^bellu<adj><m><sg>$^.<sent>$^.<sent>$
*:lex:
1:SELECT:0.8:Su<det><def><f><sg>:2:The<det><def><f><sg>
^Su<det><def><f><sg>/The<det><def><f><sg>$ ^Frantza<np><top><f><sg>/France<np><top><f><sg>$ ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$ ^unu<det><ind><m><sg>/a<det><ind><m><sg>$ ^paisu<n><m><sg>/country<n><sg>$ ^bellu<adj><m><sg>/beautiful<adj><m><sg>$^.<sent>/.<sent>$^.<sent>/.<sent>$
*:transfer:
Applying rule 4 (line 58): ^Su<det><def><f><sg>/The<det><def><f><sg>$ ^Frantza<np><top><f><sg>/France<np><top><f><sg>$
Applying rule 6 (line 61): ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$
Applying rule 1 (line 54): ^paisu<n><m><sg>/country<n><sg>$ ^bellu<adj><m><sg>/beautiful<adj><m><sg>$
Applying rule 3 (line 57): ^unu<det><ind><m><sg>/a<det><ind><m><sg>$ ^default<NP><PD><ND>{^paisu<n><m><sg>/country<n><sg>$ ^bellu<adj><m><sg>/beautiful<adj><m><sg>$}$
Applying rule 8 (line 64): ^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><m><sg>/a<det><ind><m><sg>$ ^default<NP><PD><ND>{^paisu<n><m><sg>/country<n><sg>$ ^bellu<adj><m><sg>/beautiful<adj><m><sg>$}$}$
Applying rule 9 (line 66): ^Default<DP><PD><ND>{^Su<det><def><f><sg>/The<det><def><f><sg>$ ^Frantza<np><top><f><sg>/France<np><top><f><sg>$}$ ^be<VP><p3><sg>{^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><m><sg>/a<det><ind><m><sg>$ ^default<NP><PD><ND>{^paisu<n><m><sg>/country<n><sg>$ ^bellu<adj><m><sg>/beautiful<adj><m><sg>$}$}$}$
Applying output rule 8 (line 66): Be<#S><p3><sg> -> ^Default<DP><PD><ND>{^Su<det><def><f><sg>/The<det><def><f><sg>$ ^Frantza<np><top><f><sg>/France<np><top><f><sg>$}$ ^be<VP><p3><sg>{^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><m><sg>/a<det><ind><m><sg>$ ^default<NP><PD><ND>{^paisu<n><m><sg>/country<n><sg>$ ^bellu<adj><m><sg>/beautiful<adj><m><sg>$}$}$}$
Applying output rule 3 (line 58): Default<DP><p3><sg> -> ^Su<det><def><f><sg>/The<det><def><f><sg>$ ^Frantza<np><top><f><sg>/France<np><top><f><sg>$
No rule specified: ^France<np><top><sg>$
Applying output rule 7 (line 64): be<VP><p3><sg> -> ^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><m><sg>/a<det><ind><m><sg>$ ^default<NP><PD><ND>{^paisu<n><m><sg>/country<n><sg>$ ^bellu<adj><m><sg>/beautiful<adj><m><sg>$}$}$
Applying output rule 5 (line 61): be<vP><p3><sg> -> ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$
No rule specified: ^be<vbser><pres><p3><sg>$
Applying output rule 2 (line 57): default<DP><p3><sg> -> ^unu<det><ind><m><sg>/a<det><ind><m><sg>$ ^default<NP><PD><ND>{^paisu<n><m><sg>/country<n><sg>$ ^bellu<adj><m><sg>/beautiful<adj><m><sg>$}$
No rule specified: ^a<det><ind><sg>$
Applying output rule 0 (line 54): default<NP><p3><sg> -> ^paisu<n><m><sg>/country<n><sg>$ ^bellu<adj><m><sg>/beautiful<adj><m><sg>$
No rule specified: ^beautiful<adj>$
No rule specified: ^country<n><sg>$
No rule specified: ^.<sent>/.<sent>$
No rule specified: ^.<sent>/.<sent>$
^France<np><top><sg>$ ^be<vbser><pres><p3><sg>$ ^a<det><ind><sg>$ ^beautiful<adj>$ ^country<n><sg>$^.<sent>$^.<sent>$
*:abc-xyz:
France is a beautiful country.

====Item 2: Noun-adjective order in noun phraseology: adjectives now come before the noun in translations when necessary:====
*Ex: {{transferTest|srd|eng|Su sardu est una limba antica.|Sardinian is an ancient language.}}
*Outputs for:
*:tagger: ^Su<det><def><m><sg>$ ^sardu<n><m><sg>$ ^èssere<vbser><pri><p3><sg>$ ^unu<det><ind><f><sg>$ ^limba<n><f><sg>$ ^anticu<adj><f><sg>$^.<sent>$^.<sent>$
*:lex:
1:SELECT:0.8:Su<det><def><m><sg>:2:The<det><def><m><sg>
^Su<det><def><m><sg>/The<det><def><m><sg>$ ^sardu<n><m><sg>/Sardinian<n><sg>$ ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$ ^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$^.<sent>/.<sent>$^.<sent>/.<sent>$
*:transfer:
No rule specified: ^Su<det><def><m><sg>/The<det><def><m><sg>$
No rule specified: ^sardu<n><m><sg>/Sardinian<n><sg>$
Applying rule 6 (line 61): ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$
Applying rule 1 (line 54): ^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$
Applying rule 3 (line 57): ^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$}$
Applying rule 8 (line 64): ^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$}$}$
Applying rule 10 (line 67): ^be<VP><p3><sg>{^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$}$}$}$
Applying output rule 9 (line 67): be<#S><p3><sg> -> ^be<VP><p3><sg>{^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$}$}$}$
No rule specified: ^prpers<prn><subj><p3><nt><sg>$
Applying output rule 7 (line 64): be<VP><p3><sg> -> ^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$}$}$
Applying output rule 5 (line 61): be<vP><p3><sg> -> ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$
No rule specified: ^be<vbser><pres><p3><sg>$
Applying output rule 2 (line 57): default<DP><p3><sg> -> ^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$}$
No rule specified: ^a<det><ind><sg>$
Applying output rule 0 (line 54): default<NP><p3><sg> -> ^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$
No rule specified: ^ancient<adj>$
No rule specified: ^language<n><sg>$
No rule specified: ^.<sent>/.<sent>$
No rule specified: ^.<sent>/.<sent>$
^The<det><def><m><sg>$ ^Sardinian<n><sg>$ ^prpers<prn><subj><p3><nt><sg>$ ^be<vbser><pres><p3><sg>$ ^a<det><ind><sg>$ ^ancient<adj>$ ^language<n><sg>$^.<sent>$^.<sent>$
*:abc-xyz:
#The Sardinian it is an ancient language.

====Item 3: Posessive determiner/marker order in noun phraseology====
*Ex: {{transferTest|srd|eng|Libru meu est.|It is my book.}}
*Outputs for:
*:tagger: ^Libru<n><m><sg>$ ^meu<adj><pos><m><sg>$ ^èssere<vbser><pri><p3><sg>$^.<sent>$^.<sent>$
*:lex: ^Libru<n><m><sg>/Book<n><sg>$ ^meu<adj><pos><m><sg>/my<det><pos><m><sg>$ ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$^.<sent>/.<sent>$^.<sent>/.<sent>$
*:transfer:
Applying rule 1 (line 54): ^Libru<n><m><sg>/Book<n><sg>$ ^meu<adj><pos><m><sg>/my<det><pos><m><sg>$
Applying output rule 0 (line 54): Default<NP><PD><ND> -> ^Libru<n><m><sg>/Book<n><sg>$ ^meu<adj><pos><m><sg>/my<det><pos><m><sg>$
No rule specified: ^my<det>$
No rule specified: ^Book<n><sg>$
Applying rule 6 (line 61): ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$
Applying output rule 5 (line 61): be<vP><p3><sg> -> ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$
No rule specified: ^be<vbser><pres><p3><sg>$
No rule specified: ^.<sent>/.<sent>$
No rule specified: ^.<sent>/.<sent>$
^my<det>$ ^Book<n><sg>$ ^be<vbser><pres><p3><sg>$^.<sent>$^.<sent>$
*:abc-xyz:
#my Book is.

====Item 4: For most uses/conjugations of verbs in Sardinian, the verb stands on its own without a personal pronoun, while in English personal pronouns always precede any conjugated verbs. In other words, the tags of "appo" (I have) determine a new word "I" which precedes "have" in the English translation.====
*Ex: {{transferTest|srd|eng|Appo pèrditu duos de sos libros meos.|I have lost two of my books.}}
*Outputs for:
*:tagger: ^Àere<vbhaver><pri><p1><sg>$ ^pèrdere<vblex><pp><m><sg>$ ^duos<num><m><sp>$ ^de<pr>$ ^su<det><def><m><pl>$ ^libru<n><m><pl>$ ^meu<adj><pos><m><pl>$^.<sent>$^.<sent>$
*:lex:
1:SELECT:1:de<pr>:2:of<pr>
1:SELECT:0.8:su<det><def><m><pl>:2:the<det><def><m><pl>
^Àere<vbhaver><pri><p1><sg>/Have<vbhaver><pri><p1><sg>$ ^pèrdere<vblex><pp><m><sg>/lose<vblex><pp><m><sg>$ ^duos<num><m><sp>/two<num><m><sp>$ ^de<pr>/of<pr>$ ^su<det><def><m><pl>/the<det><def><m><pl>$ ^libru<n><m><pl>/book<n><pl>$ ^meu<adj><pos><m><pl>/my<det><pos><m><pl>$^.<sent>/.<sent>$^.<sent>/.<sent>$
*:transfer:
Applying rule 5 (line 60): ^Àere<vbhaver><pri><p1><sg>/Have<vbhaver><pri><p1><sg>$
Applying output rule 4 (line 60): Have<vP><p1><sg> -> ^Àere<vbhaver><pri><p1><sg>/Have<vbhaver><pri><p1><sg>$
No rule specified: ^Have<vbhaver><pres><p1><sg>$
Applying rule 7 (line 62): ^pèrdere<vblex><pp><m><sg>/lose<vblex><pp><m><sg>$
Applying output rule 6 (line 62): lose<vP><PD><sg> -> ^pèrdere<vblex><pp><m><sg>/lose<vblex><pp><m><sg>$
No rule specified: ^lose<vblex><p3><sg>$
No rule specified: ^duos<num><m><sp>/two<num><m><sp>$
No rule specified: ^de<pr>/of<pr>$
Applying rule 1 (line 54): ^libru<n><m><pl>/book<n><pl>$ ^meu<adj><pos><m><pl>/my<det><pos><m><pl>$
Applying rule 3 (line 57): ^su<det><def><m><pl>/the<det><def><m><pl>$ ^default<NP><PD><ND>{^libru<n><m><pl>/book<n><pl>$ ^meu<adj><pos><m><pl>/my<det><pos><m><pl>$}$
Applying output rule 2 (line 57): default<DP><PD><ND> -> ^su<det><def><m><pl>/the<det><def><m><pl>$ ^default<NP><PD><ND>{^libru<n><m><pl>/book<n><pl>$ ^meu<adj><pos><m><pl>/my<det><pos><m><pl>$}$
No rule specified: ^the<det><def><pl>$
Applying output rule 0 (line 54): default<NP><p3><sg> -> ^libru<n><m><pl>/book<n><pl>$ ^meu<adj><pos><m><pl>/my<det><pos><m><pl>$
No rule specified: ^my<det>$
No rule specified: ^book<n><pl>$
No rule specified: ^.<sent>/.<sent>$
No rule specified: ^.<sent>/.<sent>$
^Have<vbhaver><pres><p1><sg>$ ^lose<vblex><p3><sg>$ ^two<num><m><sp>$ ^of<pr>$ ^the<det><def><pl>$ ^my<det>$ ^book<n><pl>$^.<sent>$^.<sent>$
*:abc-xyz:
#Have #lose #two of the #my books.

==post evaluation==
*WER, PER, and other useful numbers, part 2:
*Coverage from monolingual transducer, part 2:
*Coverage from bilingual transducer, part 2:

[[Category:Sp23_StructuralTransfer]],[[Category:Sardinian]],[[Category:English]]

Sardinian and English/Structural transfer

2023-05-03T19:53:54Z

Rorlija1: /* .rtx rules */

==pre-evaluation==
*WER, PER, and other useful numbers:
Statistics about input files
-------------------------------------------------------
Number of words in reference: 81
Number of words in test: 80
Number of unknown words (marked with a star) in test: 14
Percentage of unknown words: 17.50 %

Results when removing unknown-word marks (stars)
-------------------------------------------------------
Edit distance: 77
Word error rate (WER): 95.06 %
Number of position-independent correct words: 12
Position-independent word error rate (PER): 85.19 %
*coverage from monolingual transducer on srd.tests:
Coverage: 97.78%
Top unknown words in the corpus:
1 paìsu
1 Lettu
*coverage from bilingual transducer on srd.tests:
Number of tokenised words in the corpus: 91
Coverage: 84.62%
Top unknown words in the corpus:
2 bellu
1 paisu
1 paìsu
1 Lettu
1 furatu
1 dinari
1 punitos
1 rica
1 datu
1 milli
1 francos
1 betzu
1 iscimpru

==.rtx rules==
====Item 1: Determiners before nouns in Sardinian are omitted in English translations that do not include determiners before nouns====
*Ex: {{transferTest|srd|eng|Sa Frantza est unu paisu bellu.|France is a beautiful country.}}
*Outputs for:
*:tagger: ^Su<det><def><f><sg>$ ^Frantza<np><top><f><sg>$ ^èssere<vbser><pri><p3><sg>$ ^unu<det><ind><m><sg>$ ^paisu<n><m><sg>$ ^bellu<adj><m><sg>$^.<sent>$^.<sent>$
*:lex:
1:SELECT:0.8:Su<det><def><f><sg>:2:The<det><def><f><sg>
^Su<det><def><f><sg>/The<det><def><f><sg>$ ^Frantza<np><top><f><sg>/France<np><top><f><sg>$ ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$ ^unu<det><ind><m><sg>/a<det><ind><m><sg>$ ^paisu<n><m><sg>/country<n><sg>$ ^bellu<adj><m><sg>/beautiful<adj><m><sg>$^.<sent>/.<sent>$^.<sent>/.<sent>$
*:transfer:
Applying rule 4 (line 58): ^Su<det><def><f><sg>/The<det><def><f><sg>$ ^Frantza<np><top><f><sg>/France<np><top><f><sg>$
Applying rule 6 (line 61): ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$
Applying rule 1 (line 54): ^paisu<n><m><sg>/country<n><sg>$ ^bellu<adj><m><sg>/beautiful<adj><m><sg>$
Applying rule 3 (line 57): ^unu<det><ind><m><sg>/a<det><ind><m><sg>$ ^default<NP><PD><ND>{^paisu<n><m><sg>/country<n><sg>$ ^bellu<adj><m><sg>/beautiful<adj><m><sg>$}$
Applying rule 8 (line 64): ^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><m><sg>/a<det><ind><m><sg>$ ^default<NP><PD><ND>{^paisu<n><m><sg>/country<n><sg>$ ^bellu<adj><m><sg>/beautiful<adj><m><sg>$}$}$
Applying rule 9 (line 66): ^Default<DP><PD><ND>{^Su<det><def><f><sg>/The<det><def><f><sg>$ ^Frantza<np><top><f><sg>/France<np><top><f><sg>$}$ ^be<VP><p3><sg>{^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><m><sg>/a<det><ind><m><sg>$ ^default<NP><PD><ND>{^paisu<n><m><sg>/country<n><sg>$ ^bellu<adj><m><sg>/beautiful<adj><m><sg>$}$}$}$
Applying output rule 8 (line 66): Be<#S><p3><sg> -> ^Default<DP><PD><ND>{^Su<det><def><f><sg>/The<det><def><f><sg>$ ^Frantza<np><top><f><sg>/France<np><top><f><sg>$}$ ^be<VP><p3><sg>{^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><m><sg>/a<det><ind><m><sg>$ ^default<NP><PD><ND>{^paisu<n><m><sg>/country<n><sg>$ ^bellu<adj><m><sg>/beautiful<adj><m><sg>$}$}$}$
Applying output rule 3 (line 58): Default<DP><p3><sg> -> ^Su<det><def><f><sg>/The<det><def><f><sg>$ ^Frantza<np><top><f><sg>/France<np><top><f><sg>$
No rule specified: ^France<np><top><sg>$
Applying output rule 7 (line 64): be<VP><p3><sg> -> ^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><m><sg>/a<det><ind><m><sg>$ ^default<NP><PD><ND>{^paisu<n><m><sg>/country<n><sg>$ ^bellu<adj><m><sg>/beautiful<adj><m><sg>$}$}$
Applying output rule 5 (line 61): be<vP><p3><sg> -> ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$
No rule specified: ^be<vbser><pres><p3><sg>$
Applying output rule 2 (line 57): default<DP><p3><sg> -> ^unu<det><ind><m><sg>/a<det><ind><m><sg>$ ^default<NP><PD><ND>{^paisu<n><m><sg>/country<n><sg>$ ^bellu<adj><m><sg>/beautiful<adj><m><sg>$}$
No rule specified: ^a<det><ind><sg>$
Applying output rule 0 (line 54): default<NP><p3><sg> -> ^paisu<n><m><sg>/country<n><sg>$ ^bellu<adj><m><sg>/beautiful<adj><m><sg>$
No rule specified: ^beautiful<adj>$
No rule specified: ^country<n><sg>$
No rule specified: ^.<sent>/.<sent>$
No rule specified: ^.<sent>/.<sent>$
^France<np><top><sg>$ ^be<vbser><pres><p3><sg>$ ^a<det><ind><sg>$ ^beautiful<adj>$ ^country<n><sg>$^.<sent>$^.<sent>$
*:abc-xyz:
France is a beautiful country.

====Item 2: Noun-adjective order in noun phraseology: adjectives now come before the noun in translations when necessary:====
*Ex: {{transferTest|srd|eng|Su sardu est una limba antica.|Sardinian is an ancient language.}}
*Outputs for:
*:tagger: ^Su<det><def><m><sg>$ ^sardu<n><m><sg>$ ^èssere<vbser><pri><p3><sg>$ ^unu<det><ind><f><sg>$ ^limba<n><f><sg>$ ^anticu<adj><f><sg>$^.<sent>$^.<sent>$
*:lex:
1:SELECT:0.8:Su<det><def><m><sg>:2:The<det><def><m><sg>
^Su<det><def><m><sg>/The<det><def><m><sg>$ ^sardu<n><m><sg>/Sardinian<n><sg>$ ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$ ^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$^.<sent>/.<sent>$^.<sent>/.<sent>$
*:transfer:
No rule specified: ^Su<det><def><m><sg>/The<det><def><m><sg>$
No rule specified: ^sardu<n><m><sg>/Sardinian<n><sg>$
Applying rule 6 (line 61): ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$
Applying rule 1 (line 54): ^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$
Applying rule 3 (line 57): ^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$}$
Applying rule 8 (line 64): ^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$}$}$
Applying rule 10 (line 67): ^be<VP><p3><sg>{^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$}$}$}$
Applying output rule 9 (line 67): be<#S><p3><sg> -> ^be<VP><p3><sg>{^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$}$}$}$
No rule specified: ^prpers<prn><subj><p3><nt><sg>$
Applying output rule 7 (line 64): be<VP><p3><sg> -> ^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$}$}$
Applying output rule 5 (line 61): be<vP><p3><sg> -> ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$
No rule specified: ^be<vbser><pres><p3><sg>$
Applying output rule 2 (line 57): default<DP><p3><sg> -> ^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$}$
No rule specified: ^a<det><ind><sg>$
Applying output rule 0 (line 54): default<NP><p3><sg> -> ^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$
No rule specified: ^ancient<adj>$
No rule specified: ^language<n><sg>$
No rule specified: ^.<sent>/.<sent>$
No rule specified: ^.<sent>/.<sent>$
^The<det><def><m><sg>$ ^Sardinian<n><sg>$ ^prpers<prn><subj><p3><nt><sg>$ ^be<vbser><pres><p3><sg>$ ^a<det><ind><sg>$ ^ancient<adj>$ ^language<n><sg>$^.<sent>$^.<sent>$
*:abc-xyz:
#The Sardinian it is an ancient language.

====Item 3: Posessive determiner/marker order in noun phraseology====
*Ex: {{transferTest|srd|eng|Libru meu est.|It is my book.}}
*Outputs for:
*:tagger: ^Libru<n><m><sg>$ ^meu<adj><pos><m><sg>$ ^èssere<vbser><pri><p3><sg>$^.<sent>$^.<sent>$
*:lex: ^Libru<n><m><sg>/Book<n><sg>$ ^meu<adj><pos><m><sg>/my<det><pos><m><sg>$ ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$^.<sent>/.<sent>$^.<sent>/.<sent>$
*:transfer:
Applying rule 1 (line 54): ^Libru<n><m><sg>/Book<n><sg>$ ^meu<adj><pos><m><sg>/my<det><pos><m><sg>$
Applying output rule 0 (line 54): Default<NP><PD><ND> -> ^Libru<n><m><sg>/Book<n><sg>$ ^meu<adj><pos><m><sg>/my<det><pos><m><sg>$
No rule specified: ^my<det>$
No rule specified: ^Book<n><sg>$
Applying rule 6 (line 61): ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$
Applying output rule 5 (line 61): be<vP><p3><sg> -> ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$
No rule specified: ^be<vbser><pres><p3><sg>$
No rule specified: ^.<sent>/.<sent>$
No rule specified: ^.<sent>/.<sent>$
^my<det>$ ^Book<n><sg>$ ^be<vbser><pres><p3><sg>$^.<sent>$^.<sent>$
*:abc-xyz:
#my Book is.

====Item 4: For most uses/conjugations of verbs in Sardinian, the verb stands on its own without a personal pronoun, while in English personal pronouns always precede any conjugated verbs. In other words, the tags of "appo" (I have) determine a new word "I" which precedes "have" in the English translation.====
*Ex: {{transferTest|srd|eng|Appo pèrditu duos de sos libros meos.|I have lost two of my books.}}
*Outputs for:
*:tagger: ^Àere<vbhaver><pri><p1><sg>$ ^pèrdere<vblex><pp><m><sg>$ ^duos<num><m><sp>$ ^de<pr>$ ^su<det><def><m><pl>$ ^libru<n><m><pl>$ ^meu<adj><pos><m><pl>$^.<sent>$^.<sent>$
*:lex:
1:SELECT:1:de<pr>:2:of<pr>
1:SELECT:0.8:su<det><def><m><pl>:2:the<det><def><m><pl>
^Àere<vbhaver><pri><p1><sg>/Have<vbhaver><pri><p1><sg>$ ^pèrdere<vblex><pp><m><sg>/lose<vblex><pp><m><sg>$ ^duos<num><m><sp>/two<num><m><sp>$ ^de<pr>/of<pr>$ ^su<det><def><m><pl>/the<det><def><m><pl>$ ^libru<n><m><pl>/book<n><pl>$ ^meu<adj><pos><m><pl>/my<det><pos><m><pl>$^.<sent>/.<sent>$^.<sent>/.<sent>$
*:transfer:
Applying rule 5 (line 60): ^Àere<vbhaver><pri><p1><sg>/Have<vbhaver><pri><p1><sg>$
Applying output rule 4 (line 60): Have<vP><p1><sg> -> ^Àere<vbhaver><pri><p1><sg>/Have<vbhaver><pri><p1><sg>$
No rule specified: ^Have<vbhaver><pres><p1><sg>$
Applying rule 7 (line 62): ^pèrdere<vblex><pp><m><sg>/lose<vblex><pp><m><sg>$
Applying output rule 6 (line 62): lose<vP><PD><sg> -> ^pèrdere<vblex><pp><m><sg>/lose<vblex><pp><m><sg>$
No rule specified: ^lose<vblex><p3><sg>$
No rule specified: ^duos<num><m><sp>/two<num><m><sp>$
No rule specified: ^de<pr>/of<pr>$
Applying rule 1 (line 54): ^libru<n><m><pl>/book<n><pl>$ ^meu<adj><pos><m><pl>/my<det><pos><m><pl>$
Applying rule 3 (line 57): ^su<det><def><m><pl>/the<det><def><m><pl>$ ^default<NP><PD><ND>{^libru<n><m><pl>/book<n><pl>$ ^meu<adj><pos><m><pl>/my<det><pos><m><pl>$}$
Applying output rule 2 (line 57): default<DP><PD><ND> -> ^su<det><def><m><pl>/the<det><def><m><pl>$ ^default<NP><PD><ND>{^libru<n><m><pl>/book<n><pl>$ ^meu<adj><pos><m><pl>/my<det><pos><m><pl>$}$
No rule specified: ^the<det><def><pl>$
Applying output rule 0 (line 54): default<NP><p3><sg> -> ^libru<n><m><pl>/book<n><pl>$ ^meu<adj><pos><m><pl>/my<det><pos><m><pl>$
No rule specified: ^my<det>$
No rule specified: ^book<n><pl>$
No rule specified: ^.<sent>/.<sent>$
No rule specified: ^.<sent>/.<sent>$
^Have<vbhaver><pres><p1><sg>$ ^lose<vblex><p3><sg>$ ^two<num><m><sp>$ ^of<pr>$ ^the<det><def><pl>$ ^my<det>$ ^book<n><pl>$^.<sent>$^.<sent>$
*:abc-xyz: #Have #lose #two of the #my books.

==post evaluation==
*WER, PER, and other useful numbers, part 2:
*Coverage from monolingual transducer, part 2:
*Coverage from bilingual transducer, part 2:

[[Category:Sp23_StructuralTransfer]],[[Category:Sardinian]],[[Category:English]]

Sardinian and English/Structural transfer

2023-05-03T19:52:02Z

Rorlija1: /* .rtx rules */

==pre-evaluation==
*WER, PER, and other useful numbers:
Statistics about input files
-------------------------------------------------------
Number of words in reference: 81
Number of words in test: 80
Number of unknown words (marked with a star) in test: 14
Percentage of unknown words: 17.50 %

Results when removing unknown-word marks (stars)
-------------------------------------------------------
Edit distance: 77
Word error rate (WER): 95.06 %
Number of position-independent correct words: 12
Position-independent word error rate (PER): 85.19 %
*coverage from monolingual transducer on srd.tests:
Coverage: 97.78%
Top unknown words in the corpus:
1 paìsu
1 Lettu
*coverage from bilingual transducer on srd.tests:
Number of tokenised words in the corpus: 91
Coverage: 84.62%
Top unknown words in the corpus:
2 bellu
1 paisu
1 paìsu
1 Lettu
1 furatu
1 dinari
1 punitos
1 rica
1 datu
1 milli
1 francos
1 betzu
1 iscimpru

==.rtx rules==
====Item 1: Determiners before nouns in Sardinian are omitted in English translations that do not include determiners before nouns====
*Ex: {{transferTest|srd|eng|Sa Frantza est unu paisu bellu.|France is a beautiful country.}}
*Outputs for:
*:tagger: ^Su<det><def><f><sg>$ ^Frantza<np><top><f><sg>$ ^èssere<vbser><pri><p3><sg>$ ^unu<det><ind><m><sg>$ ^paisu<n><m><sg>$ ^bellu<adj><m><sg>$^.<sent>$^.<sent>$
*:lex:
1:SELECT:0.8:Su<det><def><f><sg>:2:The<det><def><f><sg>
^Su<det><def><f><sg>/The<det><def><f><sg>$ ^Frantza<np><top><f><sg>/France<np><top><f><sg>$ ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$ ^unu<det><ind><m><sg>/a<det><ind><m><sg>$ ^paisu<n><m><sg>/country<n><sg>$ ^bellu<adj><m><sg>/beautiful<adj><m><sg>$^.<sent>/.<sent>$^.<sent>/.<sent>$
*:transfer:
Applying rule 4 (line 58): ^Su<det><def><f><sg>/The<det><def><f><sg>$ ^Frantza<np><top><f><sg>/France<np><top><f><sg>$

Applying rule 6 (line 61): ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$

Applying rule 1 (line 54): ^paisu<n><m><sg>/country<n><sg>$ ^bellu<adj><m><sg>/beautiful<adj><m><sg>$

Applying rule 3 (line 57): ^unu<det><ind><m><sg>/a<det><ind><m><sg>$ ^default<NP><PD><ND>{^paisu<n><m><sg>/country<n><sg>$ ^bellu<adj><m><sg>/beautiful<adj><m><sg>$}$

Applying rule 8 (line 64): ^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><m><sg>/a<det><ind><m><sg>$ ^default<NP><PD><ND>{^paisu<n><m><sg>/country<n><sg>$ ^bellu<adj><m><sg>/beautiful<adj><m><sg>$}$}$

Applying rule 9 (line 66): ^Default<DP><PD><ND>{^Su<det><def><f><sg>/The<det><def><f><sg>$ ^Frantza<np><top><f><sg>/France<np><top><f><sg>$}$ ^be<VP><p3><sg>{^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><m><sg>/a<det><ind><m><sg>$ ^default<NP><PD><ND>{^paisu<n><m><sg>/country<n><sg>$ ^bellu<adj><m><sg>/beautiful<adj><m><sg>$}$}$}$

Applying output rule 8 (line 66): Be<#S><p3><sg> -> ^Default<DP><PD><ND>{^Su<det><def><f><sg>/The<det><def><f><sg>$ ^Frantza<np><top><f><sg>/France<np><top><f><sg>$}$ ^be<VP><p3><sg>{^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><m><sg>/a<det><ind><m><sg>$ ^default<NP><PD><ND>{^paisu<n><m><sg>/country<n><sg>$ ^bellu<adj><m><sg>/beautiful<adj><m><sg>$}$}$}$

Applying output rule 3 (line 58): Default<DP><p3><sg> -> ^Su<det><def><f><sg>/The<det><def><f><sg>$ ^Frantza<np><top><f><sg>/France<np><top><f><sg>$

No rule specified: ^France<np><top><sg>$

Applying output rule 7 (line 64): be<VP><p3><sg> -> ^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><m><sg>/a<det><ind><m><sg>$ ^default<NP><PD><ND>{^paisu<n><m><sg>/country<n><sg>$ ^bellu<adj><m><sg>/beautiful<adj><m><sg>$}$}$

Applying output rule 5 (line 61): be<vP><p3><sg> -> ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$

No rule specified: ^be<vbser><pres><p3><sg>$

Applying output rule 2 (line 57): default<DP><p3><sg> -> ^unu<det><ind><m><sg>/a<det><ind><m><sg>$ ^default<NP><PD><ND>{^paisu<n><m><sg>/country<n><sg>$ ^bellu<adj><m><sg>/beautiful<adj><m><sg>$}$

No rule specified: ^a<det><ind><sg>$

Applying output rule 0 (line 54): default<NP><p3><sg> -> ^paisu<n><m><sg>/country<n><sg>$ ^bellu<adj><m><sg>/beautiful<adj><m><sg>$

No rule specified: ^beautiful<adj>$

No rule specified: ^country<n><sg>$

No rule specified: ^.<sent>/.<sent>$

No rule specified: ^.<sent>/.<sent>$
^France<np><top><sg>$ ^be<vbser><pres><p3><sg>$ ^a<det><ind><sg>$ ^beautiful<adj>$ ^country<n><sg>$^.<sent>$^.<sent>$
*:abc-xyz:
France is a beautiful country.

====Item 2: Noun-adjective order in noun phraseology: adjectives now come before the noun in translations when necessary:====
*Ex: {{transferTest|srd|eng|Su sardu est una limba antica.|Sardinian is an ancient language.}}
*Outputs for:
*:tagger: ^Su<det><def><m><sg>$ ^sardu<n><m><sg>$ ^èssere<vbser><pri><p3><sg>$ ^unu<det><ind><f><sg>$ ^limba<n><f><sg>$ ^anticu<adj><f><sg>$^.<sent>$^.<sent>$
*:lex:
1:SELECT:0.8:Su<det><def><m><sg>:2:The<det><def><m><sg>
^Su<det><def><m><sg>/The<det><def><m><sg>$ ^sardu<n><m><sg>/Sardinian<n><sg>$ ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$ ^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$^.<sent>/.<sent>$^.<sent>/.<sent>$
*:transfer:
No rule specified: ^Su<det><def><m><sg>/The<det><def><m><sg>$

No rule specified: ^sardu<n><m><sg>/Sardinian<n><sg>$

Applying rule 6 (line 61): ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$

Applying rule 1 (line 54): ^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$

Applying rule 3 (line 57): ^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$}$

Applying rule 8 (line 64): ^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$}$}$

Applying rule 10 (line 67): ^be<VP><p3><sg>{^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$}$}$}$

Applying output rule 9 (line 67): be<#S><p3><sg> -> ^be<VP><p3><sg>{^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$}$}$}$

No rule specified: ^prpers<prn><subj><p3><nt><sg>$

Applying output rule 7 (line 64): be<VP><p3><sg> -> ^be<vP><p3><sg>{^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$}$ ^default<DP><PD><ND>{^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$}$}$

Applying output rule 5 (line 61): be<vP><p3><sg> -> ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$

No rule specified: ^be<vbser><pres><p3><sg>$

Applying output rule 2 (line 57): default<DP><p3><sg> -> ^unu<det><ind><f><sg>/a<det><ind><f><sg>$ ^default<NP><PD><ND>{^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$}$

No rule specified: ^a<det><ind><sg>$

Applying output rule 0 (line 54): default<NP><p3><sg> -> ^limba<n><f><sg>/language<n><sg>$ ^anticu<adj><f><sg>/ancient<adj><f><sg>$

No rule specified: ^ancient<adj>$

No rule specified: ^language<n><sg>$

No rule specified: ^.<sent>/.<sent>$

No rule specified: ^.<sent>/.<sent>$
^The<det><def><m><sg>$ ^Sardinian<n><sg>$ ^prpers<prn><subj><p3><nt><sg>$ ^be<vbser><pres><p3><sg>$ ^a<det><ind><sg>$ ^ancient<adj>$ ^language<n><sg>$^.<sent>$^.<sent>$
*:abc-xyz:
#The Sardinian it is an ancient language.

====Item 3: Posessive determiner/marker order in noun phraseology====
*Ex: {{transferTest|srd|eng|Libru meu est.|It is my book.}}
*Outputs for:
*:tagger: ^Libru<n><m><sg>$ ^meu<adj><pos><m><sg>$ ^èssere<vbser><pri><p3><sg>$^.<sent>$^.<sent>$
*:lex: ^Libru<n><m><sg>/Book<n><sg>$ ^meu<adj><pos><m><sg>/my<det><pos><m><sg>$ ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$^.<sent>/.<sent>$^.<sent>/.<sent>$
*:transfer:
Applying rule 1 (line 54): ^Libru<n><m><sg>/Book<n><sg>$ ^meu<adj><pos><m><sg>/my<det><pos><m><sg>$

Applying output rule 0 (line 54): Default<NP><PD><ND> -> ^Libru<n><m><sg>/Book<n><sg>$ ^meu<adj><pos><m><sg>/my<det><pos><m><sg>$

No rule specified: ^my<det>$

No rule specified: ^Book<n><sg>$

Applying rule 6 (line 61): ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$

Applying output rule 5 (line 61): be<vP><p3><sg> -> ^èssere<vbser><pri><p3><sg>/be<vbser><pri><p3><sg>$

No rule specified: ^be<vbser><pres><p3><sg>$

No rule specified: ^.<sent>/.<sent>$

No rule specified: ^.<sent>/.<sent>$
^my<det>$ ^Book<n><sg>$ ^be<vbser><pres><p3><sg>$^.<sent>$^.<sent>$
*:abc-xyz:
#my Book is.

====Item 4: For most uses/conjugations of verbs in Sardinian, the verb stands on its own without a personal pronoun, while in English personal pronouns always precede any conjugated verbs. In other words, the tags of "appo" (I have) determine a new word "I" which precedes "have" in the English translation.====
*Ex: {{transferTest|srd|eng|Appo pèrditu duos de sos libros meos.|I have lost two of my books.}}
*Outputs for:
*:tagger: ^Àere<vbhaver><pri><p1><sg>$ ^pèrdere<vblex><pp><m><sg>$ ^duos<num><m><sp>$ ^de<pr>$ ^su<det><def><m><pl>$ ^libru<n><m><pl>$ ^meu<adj><pos><m><pl>$^.<sent>$^.<sent>$
*:lex:
1:SELECT:1:de<pr>:2:of<pr>
1:SELECT:0.8:su<det><def><m><pl>:2:the<det><def><m><pl>
^Àere<vbhaver><pri><p1><sg>/Have<vbhaver><pri><p1><sg>$ ^pèrdere<vblex><pp><m><sg>/lose<vblex><pp><m><sg>$ ^duos<num><m><sp>/two<num><m><sp>$ ^de<pr>/of<pr>$ ^su<det><def><m><pl>/the<det><def><m><pl>$ ^libru<n><m><pl>/book<n><pl>$ ^meu<adj><pos><m><pl>/my<det><pos><m><pl>$^.<sent>/.<sent>$^.<sent>/.<sent>$
*:transfer:
Applying rule 5 (line 60): ^Àere<vbhaver><pri><p1><sg>/Have<vbhaver><pri><p1><sg>$

Applying output rule 4 (line 60): Have<vP><p1><sg> -> ^Àere<vbhaver><pri><p1><sg>/Have<vbhaver><pri><p1><sg>$

No rule specified: ^Have<vbhaver><pres><p1><sg>$

Applying rule 7 (line 62): ^pèrdere<vblex><pp><m><sg>/lose<vblex><pp><m><sg>$

Applying output rule 6 (line 62): lose<vP><PD><sg> -> ^pèrdere<vblex><pp><m><sg>/lose<vblex><pp><m><sg>$

No rule specified: ^lose<vblex><p3><sg>$

No rule specified: ^duos<num><m><sp>/two<num><m><sp>$

No rule specified: ^de<pr>/of<pr>$

Applying rule 1 (line 54): ^libru<n><m><pl>/book<n><pl>$ ^meu<adj><pos><m><pl>/my<det><pos><m><pl>$

Applying rule 3 (line 57): ^su<det><def><m><pl>/the<det><def><m><pl>$ ^default<NP><PD><ND>{^libru<n><m><pl>/book<n><pl>$ ^meu<adj><pos><m><pl>/my<det><pos><m><pl>$}$

Applying output rule 2 (line 57): default<DP><PD><ND> -> ^su<det><def><m><pl>/the<det><def><m><pl>$ ^default<NP><PD><ND>{^libru<n><m><pl>/book<n><pl>$ ^meu<adj><pos><m><pl>/my<det><pos><m><pl>$}$

No rule specified: ^the<det><def><pl>$

Applying output rule 0 (line 54): default<NP><p3><sg> -> ^libru<n><m><pl>/book<n><pl>$ ^meu<adj><pos><m><pl>/my<det><pos><m><pl>$

No rule specified: ^my<det>$

No rule specified: ^book<n><pl>$

No rule specified: ^.<sent>/.<sent>$

No rule specified: ^.<sent>/.<sent>$
^Have<vbhaver><pres><p1><sg>$ ^lose<vblex><p3><sg>$ ^two<num><m><sp>$ ^of<pr>$ ^the<det><def><pl>$ ^my<det>$ ^book<n><pl>$^.<sent>$^.<sent>$
*:abc-xyz: #Have #lose #two of the #my books.

==post evaluation==
*WER, PER, and other useful numbers, part 2:
*Coverage from monolingual transducer, part 2:
*Coverage from bilingual transducer, part 2:

[[Category:Sp23_StructuralTransfer]],[[Category:Sardinian]],[[Category:English]]

Sardinian and English/Structural transfer

2023-05-03T19:42:05Z

Rorlija1: /* Item 2: Noun-adjective order in noun phraseology: adjectives now come before the noun in translations when necessary: */

Sardinian and English/Structural transfer

2023-05-03T19:41:29Z

Rorlija1: /* .rtx rules */

Sardinian and English/Structural transfer

2023-05-03T19:39:52Z

Rorlija1: /* .rtx rules */

Sardinian and English/Contrastive Grammar

2023-05-03T19:19:07Z

Rorlija1: /* srd → eng transfer morph tests */

==Differences in parse and corresponding examples==
*Difference #1: Sardinian requires a determiner before a noun in some instances for which English does not use a determiner before a noun.
*:Example #1: {{transferTest|srd|eng|'''Su''' sardu est una limba antica.|Sardinian is an ancient language.}}
*:Example #2: {{transferTest|srd|eng|'''Sa''' Frantza est unu paisu bellu.|France is a beautiful country.}}

*Difference #2: In this construction, adjectives in Sardinian come after the noun, whereas they come before the noun in English.
*:Example #1: {{transferTest|srd|eng|Su sardu est una limba '''antica'''.|Sardinian is an '''ancient''' language.}}
*:Example #2: {{transferTest|srd|eng|Sa Frantza est unu paisu '''bellu'''.|France is a '''beautiful''' country.}}

*Difference #3: The posessive pronoun comes after the noun in Sardinian rather than before the noun as is the case in English.
*:Example #1: {{transferTest|srd|eng|Appo pèrditu duos de sos libros '''meos'''.|I have lost two of '''my''' books.}}
*:Example #2: {{transferTest|srd|eng|Lettu '''meu''' est.|It is '''my''' bed.}}

*Difference #4: For most uses/conjugations of verbs in Sardinian, the verb stands on its own without a personal pronoun, while in English personal pronouns always precede any conjugated verbs. In other words, the tags of "appo" (I have) determine a new word "I" which precedes "have" in the English translation.
*:Example #1: {{transferTest|srd|eng|Appo pèrditu duos de sos libros meos.|'''I''' have lost two of my books.}}
*:Example #2: {{transferTest|srd|eng|M'an natu ki su trenu devíat arrivare a sas nove.|'''They''' told me that the train was supposed to arrive at nine.}}
*::Also, here, note that the Sardinian uses an auxiliary verb whereas the English does not! Another difference! (an natu = they told)

*Difference #5: Information carried by the gender tag in Sardinian nouns referring to people produces a new word in English.
*:Example #1: {{transferTest|srd|eng|Custa rica at datu milli francos a su betzu.|This rich '''woman''' gave a thousand francs to the old man.}}
*:Example #2: {{transferTest|srd|eng|Ses un'iscimpru.|You are a stupid '''man'''.}}

*Not a real contrastive difference that matters for srd -> eng, but another thing to keep in mind: "The" does not change form in English, but "su" in Sardinian must agree with the noun which it precedes in number and gender.
*:Example #1: {{transferTest|srd|eng|'''Sos''' ki an furatu su dinari at a èssere punitos.|'''The''' people who stole the money will be punished.}}
*:Example #2: {{transferTest|srd|eng|Una de '''sas''' berbekes est maláida.|One of '''the''' sheep is sick.}}

==srd → eng transfer morph tests==
*Diff.1/2, Ex.1:
*: {{transferMorphTest|srd|eng|Su{{tag|det}}{{tag|def}}{{tag|m}}{{tag|sg}} sardu{{tag|n}}{{tag|m}}{{tag|sg}} èssere{{tag|vbser}}{{tag|pri}}{{tag|p3}}{{tag|sg}} unu{{tag|det}}{{tag|ind}}{{tag|f}}{{tag|sg}} limba{{tag|n}}{{tag|f}}{{tag|sg}} anticu{{tag|adj}}{{tag|f}}{{tag|sg}}|Sardinian{{tag|n}}{{tag|sg}} be{{tag|vbser}}{{tag|pres}}{{tag|p3}}{{tag|sg}} a{{tag|det}}{{tag|ind}}{{tag|sg}} ancient{{tag|adj}} language{{tag|n}}{{tag|sg}}}}
*Diff.1/2, Ex.2:
*: {{transferMorphTest|srd|eng|Su{{tag|det}}{{tag|def}}{{tag|f}}{{tag|sg}} Frantza{{tag|np}}{{tag|top}}{{tag|f}}{{tag|sg}} èssere{{tag|vbser}}{{tag|pri}}{{tag|p3}}{{tag|sg}} unu{{tag|det}}{{tag|ind}}{{tag|m}}{{tag|sg}} paisu{{tag|n}}{{tag|m}}{{tag|sg}} bellu{{tag|adj}}{{tag|m}}{{tag|sg}}|France{{tag|np}}{{tag|top}}{{tag|sg}} be{{tag|vbser}}{{tag|pres}}{{tag|p3}}{{tag|sg}} a{{tag|det}}{{tag|ind}}{{tag|sg}} beautiful{{tag|adj}} country{{tag|n}}{{tag|sg}}}}
*Diff.3/4, Ex.1:
*: {{transferMorphTest|srd|eng|àere{{tag|vbhaver}}{{tag|pri}}{{tag|p1}}{{tag|sg}} pèrdere{{tag|vblex}}{{tag|pp}}{{tag|m}}{{tag|sg}} duos{{tag|num}}{{tag|mf}}{{tag|sp}} de{{tag|pr}} su{{tag|det}}{{tag|def}}{{tag|m}}{{tag|pl}} libru{{tag|n}}{{tag|m}}{{tag|pl}} meu{{tag|adj}}{{tag|pos}}{{tag|m}}{{tag|pl}}|prpers{{tag|prn}}{{tag|subj}}{{tag|p1}}{{tag|mf}}{{tag|sg}} have{{tag|vbhaver}}{{tag|pres}} lose{{tag|vblex}}{{tag|pp}} two{{tag|num}}{{tag|pl}} of{{tag|pr}} my{{tag|det}}{{tag|pos}}{{tag|sp}} book{{tag|n}}{{tag|pl}}}}
*Diff.3, Ex.2:
*: {{transferMorphTest|srd|eng|lettu{{tag|n}}{{tag|m}}{{tag|sg}} meu{{tag|adj}}{{tag|pos}}{{tag|m}}{{tag|sg}} èssere{{tag|vbser}}{{tag|pri}}{{tag|p3}}{{tag|sg}}|prpers{{tag|prn}}{{tag|subj}}{{tag|p3}}{{tag|nt}}{{tag|sg}} be{{tag|vbser}}{{tag|pres}}{{tag|p3}}{{tag|sg}} my{{tag|det}}{{tag|pos}}{{tag|sp}} bed{{tag|n}}{{tag|sg}}}}
*Diff.4, Ex.2:
*: {{transferMorphTest|srd|eng|Mi{{tag|prn}}{{tag|pro}}{{tag|p1}}{{tag|mf}}{{tag|sg}} àere{{tag|vbhaver}}{{tag|pri}}{{tag|p3}}{{tag|pl}} nàrrere{{tag|vblex}}{{tag|pp}}{{tag|m}}{{tag|sg}} chi{{tag|cnjsub}} su{{tag|det}}{{tag|def}}{{tag|m}}{{tag|sg}} trenu{{tag|n}}{{tag|m}}{{tag|sg}} dèvere{{tag|vblex}}{{tag|pii}}{{tag|p3}}{{tag|sg}} arrivare{{tag|vblex}}{{tag|inf}} a{{tag|pr}} su{{tag|det}}{{tag|def}}{{tag|f}}{{tag|pl}} nove{{tag|num}}{{tag|mf}}{{tag|sg}}|prpers{{tag|prn}}{{tag|subj}}{{tag|p3}}{{tag|mf}}{{tag|pl}} tell{{tag|vblex}}{{tag|past}} prpers{{tag|prn}}{{tag|obj}}{{tag|p1}}{{tag|mf}}{{tag|sg}} that{{tag|cnjsub}} the{{tag|det}}{{tag|def}}{{tag|sp}} train{{tag|n}}{{tag|sg}} be{{tag|vbser}}{{tag|past}}{{tag|p3}}{{tag|sg}} suppose{{tag|vblex}}{{tag|pp}} arrive{{tag|vblex}}{{tag|inf}} at{{tag|pr}} nine{{tag|num}}{{tag|pl}}}}
*Diff.5, Ex.1:
*: {{transferMorphTest|srd|eng|custu{{tag|det}}{{tag|dem}}{{tag|f}}{{tag|sg}} ricu{{tag|n}}{{tag|f}}{{tag|sg}} àere{{tag|vbhaver}}{{tag|pri}}{{tag|p3}}{{tag|sg}} dare{{tag|vblex}}{{tag|pp}}{{tag|m}}{{tag|sg}} milli{{tag|num}}{{tag|mf}}{{tag|sp}} francu{{tag|n}}{{tag|m}}{{tag|pl}} a{{tag|pr}} su{{tag|det}}{{tag|def}}{{tag|m}}{{tag|sg}} betzu{{tag|n}}{{tag|m}}{{tag|sg}}|this{{tag|det}}{{tag|dem}}{{tag|sg}} rich{{tag|adj}}{{tag|sint}} woman{{tag|n}}{{tag|sg}} give{{tag|vblex}}{{tag|past}} a thousand{{tag|num}}{{tag|pl}} franc{{tag|n}}{{tag|pl}} to{{tag|pr}} the{{tag|det}}{{tag|def}}{{tag|sp}} old{{tag|adj}}{{tag|sint}} man{{tag|n}}{{tag|sg}}}}
*Diff.5, Ex.2:
*: {{transferMorphTest|srd|eng|èssere{{tag|vbser}}{{tag|pri}}{{tag|p2}}{{tag|sg}} unu{{tag|det}}{{tag|ind}}{{tag|m}}{{tag|sg}} iscimpru{{tag|n}}{{tag|m}}{{tag|sg}}|prpers{{tag|prn}}{{tag|subj}}{{tag|p2}}{{tag|mf}}{{tag|sp}} be{{tag|vbser}}{{tag|pres}} a{{tag|det}}{{tag|ind}}{{tag|sg}} stupid{{tag|adj}} man{{tag|n}}{{tag|sg}}}}
*Addendum, Ex.1:
*: {{transferMorphTest|srd|eng|Su{{tag|det}}{{tag|def}}{{tag|m}}{{tag|pl}} chi{{tag|cnjsub}} àere{{tag|vbhaver}}{{tag|pri}}{{tag|p3}}{{tag|pl}} furare{{tag|vblex}}{{tag|pp}}{{tag|m}}{{tag|sg}} su{{tag|det}}{{tag|def}}{{tag|m}}{{tag|sg}} dinari{{tag|n}}{{tag|m}}{{tag|sg}} àere{{tag|vbhaver}}{{tag|pri}}{{tag|p3}}{{tag|sg}} a{{tag|pr}} èssere{{tag|vbser}}{{tag|inf}} punire{{tag|vblex}}{{tag|pp}}{{tag|m}}{{tag|pl}}|the{{tag|det}}{{tag|def}}{{tag|sp}} person{{tag|n}}{{tag|pl}} who{{tag|prn}}{{tag|rel}}{{tag|an}}{{tag|mf}}{{tag|sp}} steal{{tag|vblex}}{{tag|past}} the{{tag|det}}{{tag|def}}{{tag|sp}} money{{tag|n}}{{tag|sg}} will{{tag|vbmod}}{{tag|pres}} be{{tag|vbser}}{{tag|inf}} punish{{tag|vblex}}{{tag|pp}}}}
*Addendum, Ex.2:
*: {{transferMorphTest|srd|eng|unu{{tag|prn}}{{tag|tn}}{{tag|f}}{{tag|sg}} de{{tag|pr}} su{{tag|det}}{{tag|def}}{{tag|f}}{{tag|pl}} berbeke{{tag|n}}{{tag|f}}{{tag|pl}} èssere{{tag|vbser}}{{tag|pri}}{{tag|p3}}{{tag|sg}} malàidu{{tag|adj}}{{tag|f}}{{tag|sg}}|one{{tag|prn}}{{tag|dem}}{{tag|mf}}{{tag|sg}} of{{tag|pr}} the{{tag|det}}{{tag|def}}{{tag|sp}} sheep{{tag|n}}{{tag|pl}} be{{tag|vbser}}{{tag|pres}}{{tag|p3}}{{tag|sg}} sick{{tag|adj}}{{tag|sint}}}}

[[Category:Sp23_ContrastiveGrammars]],[[Category:Sardinian]],[[Category:English]]

Sardinian and English/Contrastive Grammar

2023-05-03T19:17:04Z

Rorlija1: /* srd → eng transfer morph tests */

==Differences in parse and corresponding examples==
*Difference #1: Sardinian requires a determiner before a noun in some instances for which English does not use a determiner before a noun.
*:Example #1: {{transferTest|srd|eng|'''Su''' sardu est una limba antica.|Sardinian is an ancient language.}}
*:Example #2: {{transferTest|srd|eng|'''Sa''' Frantza est unu paisu bellu.|France is a beautiful country.}}

*Difference #2: In this construction, adjectives in Sardinian come after the noun, whereas they come before the noun in English.
*:Example #1: {{transferTest|srd|eng|Su sardu est una limba '''antica'''.|Sardinian is an '''ancient''' language.}}
*:Example #2: {{transferTest|srd|eng|Sa Frantza est unu paisu '''bellu'''.|France is a '''beautiful''' country.}}

*Difference #3: The posessive pronoun comes after the noun in Sardinian rather than before the noun as is the case in English.
*:Example #1: {{transferTest|srd|eng|Appo pèrditu duos de sos libros '''meos'''.|I have lost two of '''my''' books.}}
*:Example #2: {{transferTest|srd|eng|Lettu '''meu''' est.|It is '''my''' bed.}}

*Difference #4: For most uses/conjugations of verbs in Sardinian, the verb stands on its own without a personal pronoun, while in English personal pronouns always precede any conjugated verbs. In other words, the tags of "appo" (I have) determine a new word "I" which precedes "have" in the English translation.
*:Example #1: {{transferTest|srd|eng|Appo pèrditu duos de sos libros meos.|'''I''' have lost two of my books.}}
*:Example #2: {{transferTest|srd|eng|M'an natu ki su trenu devíat arrivare a sas nove.|'''They''' told me that the train was supposed to arrive at nine.}}
*::Also, here, note that the Sardinian uses an auxiliary verb whereas the English does not! Another difference! (an natu = they told)

*Difference #5: Information carried by the gender tag in Sardinian nouns referring to people produces a new word in English.
*:Example #1: {{transferTest|srd|eng|Custa rica at datu milli francos a su betzu.|This rich '''woman''' gave a thousand francs to the old man.}}
*:Example #2: {{transferTest|srd|eng|Ses un'iscimpru.|You are a stupid '''man'''.}}

*Not a real contrastive difference that matters for srd -> eng, but another thing to keep in mind: "The" does not change form in English, but "su" in Sardinian must agree with the noun which it precedes in number and gender.
*:Example #1: {{transferTest|srd|eng|'''Sos''' ki an furatu su dinari at a èssere punitos.|'''The''' people who stole the money will be punished.}}
*:Example #2: {{transferTest|srd|eng|Una de '''sas''' berbekes est maláida.|One of '''the''' sheep is sick.}}

==srd → eng transfer morph tests==
*Diff.1/2, Ex.1:
*: {{transferMorphTest|srd|eng|Su{{tag|det}}{{tag|def}}{{tag|m}}{{tag|sg}} sardu{{tag|n}}{{tag|m}}{{tag|sg}} èssere{{tag|vbser}}{{tag|pri}}{{tag|p3}}{{tag|sg}} unu{{tag|det}}{{tag|ind}}{{tag|f}}{{tag|sg}} limba{{tag|n}}{{tag|f}}{{tag|sg}} anticu{{tag|adj}}{{tag|f}}{{tag|sg}}|Sardinian{{tag|n}}{{tag|sg}} be{{tag|vbser}}{{tag|pres}}{{tag|p3}}{{tag|sg}} a{{tag|det}}{{tag|ind}}{{tag|sg}} ancient{{tag|adj}} language{{tag|n}}{{tag|sg}}}}
*Diff.1/2, Ex.2:
*: {{transferMorphTest|srd|eng|Su{{tag|det}}{{tag|def}}{{tag|f}}{{tag|sg}} Frantza{{tag|np}}{{tag|top}}{{tag|f}}{{tag|sg}} èssere{{tag|vbser}}{{tag|pri}}{{tag|p3}}{{tag|sg}} unu{{tag|det}}{{tag|ind}}{{tag|m}}{{tag|sg}} paisu{{tag|n}}{{tag|m}}{{tag|sg}} bellu{{tag|adj}}{{tag|m}}{{tag|sg}}|France{{tag|np}}{{tag|top}}{{tag|sg}} be{{tag|vbser}}{{tag|pres}}{{tag|p3}}{{tag|sg}} a{{tag|det}}{{tag|ind}}{{tag|sg}} beautiful{{tag|adj}} country{{tag|n}}{{tag|sg}}}}
*Diff.3/4, Ex.1:
*: {{transferMorphTest|srd|eng|àere{{tag|vbhaver}}{{tag|pri}}{{tag|p1}}{{tag|sg}} pèrdere{{tag|vblex}}{{tag|pp}}{{tag|m}}{{tag|sg}} duos{{tag|num}}{{tag|mf}}{{tag|sp}} de{{tag|pr}} su{{tag|det}}{{tag|def}}{{tag|m}}{{tag|pl}} libru{{tag|n}}{{tag|m}}{{tag|pl}} meu{{tag|adj}}{{tag|pos}}{{tag|m}}{{tag|pl}}|prpers{{tag|prn}}{{tag|subj}}{{tag|p1}}{{tag|mf}}{{tag|sg}} have{{tag|vbhaver}}{{tag|pres}} lose{{tag|vblex}}{{tag|pp}} two{{tag|num}}{{tag|pl}} of{{tag|pr}} my{{tag|det}}{{tag|pos}}{{tag|sp}} book{{tag|n}}{{tag|pl}}}}
*Diff.3, Ex.2:
*: {{transferMorphTest|srd|eng|lettu{{tag|n}}{{tag|m}}{{tag|sg}} meu{{tag|adj}}{{tag|pos}}{{tag|m}}{{tag|sg}} èssere{{tag|vbser}}{{tag|pri}}{{tag|p3}}{{tag|sg}}|prpers{{tag|prn}}{{tag|subj}}{{tag|p3}}{{tag|nt}}{{tag|sg}} be{{tag|vbser}}{{tag|pres}}{{tag|p3}}{{tag|sg}} my{{tag|det}}{{tag|pos}}{{tag|sp}} bed{{tag|n}}{{tag|sg}}}}
*Diff.4, Ex.1:
*: {{transferMorphTest|srd|eng|Su{{tag|det}}{{tag|def}}{{tag|m}}{{tag|pl}} chi{{tag|cnjsub}} àere{{tag|vbhaver}}{{tag|pri}}{{tag|p3}}{{tag|pl}} furare{{tag|vblex}}{{tag|pp}}{{tag|m}}{{tag|sg}} su{{tag|det}}{{tag|def}}{{tag|m}}{{tag|sg}} dinari{{tag|n}}{{tag|m}}{{tag|sg}} àere{{tag|vbhaver}}{{tag|pri}}{{tag|p3}}{{tag|sg}} a{{tag|pr}} èssere{{tag|vbser}}{{tag|inf}} punire{{tag|vblex}}{{tag|pp}}{{tag|m}}{{tag|pl}}|the{{tag|det}}{{tag|def}}{{tag|sp}} person{{tag|n}}{{tag|pl}} who{{tag|prn}}{{tag|rel}}{{tag|an}}{{tag|mf}}{{tag|sp}} steal{{tag|vblex}}{{tag|past}} the{{tag|det}}{{tag|def}}{{tag|sp}} money{{tag|n}}{{tag|sg}} will{{tag|vbmod}}{{tag|pres}} be{{tag|vbser}}{{tag|inf}} punish{{tag|vblex}}{{tag|pp}}
*Diff.4, Ex.2:
*: {{transferMorphTest|srd|eng|unu{{tag|prn}}{{tag|tn}}{{tag|f}}{{tag|sg}} de{{tag|pr}} su{{tag|det}}{{tag|def}}{{tag|f}}{{tag|pl}} berbeke{{tag|n}}{{tag|f}}{{tag|pl}} èssere{{tag|vbser}}{{tag|pri}}{{tag|p3}}{{tag|sg}} malàidu{{tag|adj}}{{tag|f}}{{tag|sg}}|one{{tag|prn}}{{tag|dem}}{{tag|mf}}{{tag|sg}} of{{tag|pr}} the{{tag|det}}{{tag|def}}{{tag|sp}} sheep{{tag|n}}{{tag|pl}} be{{tag|vbser}}{{tag|pres}}{{tag|p3}}{{tag|sg}} sick{{tag|adj}}{{tag|sint}}}}
*Diff.4, Ex.2:
*: {{transferMorphTest|srd|eng|Mi{{tag|prn}}{{tag|pro}}{{tag|p1}}{{tag|mf}}{{tag|sg}} àere{{tag|vbhaver}}{{tag|pri}}{{tag|p3}}{{tag|pl}} nàrrere{{tag|vblex}}{{tag|pp}}{{tag|m}}{{tag|sg}} chi{{tag|cnjsub}} su{{tag|det}}{{tag|def}}{{tag|m}}{{tag|sg}} trenu{{tag|n}}{{tag|m}}{{tag|sg}} dèvere{{tag|vblex}}{{tag|pii}}{{tag|p3}}{{tag|sg}} arrivare{{tag|vblex}}{{tag|inf}} a{{tag|pr}} su{{tag|det}}{{tag|def}}{{tag|f}}{{tag|pl}} nove{{tag|num}}{{tag|mf}}{{tag|sg}}|prpers{{tag|prn}}{{tag|subj}}{{tag|p3}}{{tag|mf}}{{tag|pl}} tell{{tag|vblex}}{{tag|past}} prpers{{tag|prn}}{{tag|obj}}{{tag|p1}}{{tag|mf}}{{tag|sg}} that{{tag|cnjsub}} the{{tag|det}}{{tag|def}}{{tag|sp}} train{{tag|n}}{{tag|sg}} be{{tag|vbser}}{{tag|past}}{{tag|p3}}{{tag|sg}} suppose{{tag|vblex}}{{tag|pp}} arrive{{tag|vblex}}{{tag|inf}} at{{tag|pr}} nine{{tag|num}}{{tag|pl}}}}
*Diff.5, Ex.1:
*: {{transferMorphTest|srd|eng|custu{{tag|det}}{{tag|dem}}{{tag|f}}{{tag|sg}} ricu{{tag|n}}{{tag|f}}{{tag|sg}} àere{{tag|vbhaver}}{{tag|pri}}{{tag|p3}}{{tag|sg}} dare{{tag|vblex}}{{tag|pp}}{{tag|m}}{{tag|sg}} milli{{tag|num}}{{tag|mf}}{{tag|sp}} francu{{tag|n}}{{tag|m}}{{tag|pl}} a{{tag|pr}} su{{tag|det}}{{tag|def}}{{tag|m}}{{tag|sg}} betzu{{tag|n}}{{tag|m}}{{tag|sg}}|this{{tag|det}}{{tag|dem}}{{tag|sg}} rich{{tag|adj}}{{tag|sint}} woman{{tag|n}}{{tag|sg}} give{{tag|vblex}}{{tag|past}} a thousand{{tag|num}}{{tag|pl}} franc{{tag|n}}{{tag|pl}} to{{tag|pr}} the{{tag|det}}{{tag|def}}{{tag|sp}} old{{tag|adj}}{{tag|sint}} man{{tag|n}}{{tag|sg}}}}
*Diff.5, Ex.2:
*: {{transferMorphTest|srd|eng|èssere{{tag|vbser}}{{tag|pri}}{{tag|p2}}{{tag|sg}} unu{{tag|det}}{{tag|ind}}{{tag|m}}{{tag|sg}} iscimpru{{tag|n}}{{tag|m}}{{tag|sg}}|prpers{{tag|prn}}{{tag|subj}}{{tag|p2}}{{tag|mf}}{{tag|sp}} be{{tag|vbser}}{{tag|pres}} a{{tag|det}}{{tag|ind}}{{tag|sg}} stupid{{tag|adj}} man{{tag|n}}{{tag|sg}}}}

[[Category:Sp23_ContrastiveGrammars]],[[Category:Sardinian]],[[Category:English]]

Sardinian and English/Contrastive Grammar

2023-05-03T19:15:49Z

Rorlija1: /* Differences in parse and corresponding examples */

==Differences in parse and corresponding examples==
*Difference #1: Sardinian requires a determiner before a noun in some instances for which English does not use a determiner before a noun.
*:Example #1: {{transferTest|srd|eng|'''Su''' sardu est una limba antica.|Sardinian is an ancient language.}}
*:Example #2: {{transferTest|srd|eng|'''Sa''' Frantza est unu paisu bellu.|France is a beautiful country.}}

*Difference #2: In this construction, adjectives in Sardinian come after the noun, whereas they come before the noun in English.
*:Example #1: {{transferTest|srd|eng|Su sardu est una limba '''antica'''.|Sardinian is an '''ancient''' language.}}
*:Example #2: {{transferTest|srd|eng|Sa Frantza est unu paisu '''bellu'''.|France is a '''beautiful''' country.}}

*Difference #3: The posessive pronoun comes after the noun in Sardinian rather than before the noun as is the case in English.
*:Example #1: {{transferTest|srd|eng|Appo pèrditu duos de sos libros '''meos'''.|I have lost two of '''my''' books.}}
*:Example #2: {{transferTest|srd|eng|Lettu '''meu''' est.|It is '''my''' bed.}}

*Difference #4: For most uses/conjugations of verbs in Sardinian, the verb stands on its own without a personal pronoun, while in English personal pronouns always precede any conjugated verbs. In other words, the tags of "appo" (I have) determine a new word "I" which precedes "have" in the English translation.
*:Example #1: {{transferTest|srd|eng|Appo pèrditu duos de sos libros meos.|'''I''' have lost two of my books.}}
*:Example #2: {{transferTest|srd|eng|M'an natu ki su trenu devíat arrivare a sas nove.|'''They''' told me that the train was supposed to arrive at nine.}}
*::Also, here, note that the Sardinian uses an auxiliary verb whereas the English does not! Another difference! (an natu = they told)

*Difference #5: Information carried by the gender tag in Sardinian nouns referring to people produces a new word in English.
*:Example #1: {{transferTest|srd|eng|Custa rica at datu milli francos a su betzu.|This rich '''woman''' gave a thousand francs to the old man.}}
*:Example #2: {{transferTest|srd|eng|Ses un'iscimpru.|You are a stupid '''man'''.}}

*Not a real contrastive difference that matters for srd -> eng, but another thing to keep in mind: "The" does not change form in English, but "su" in Sardinian must agree with the noun which it precedes in number and gender.
*:Example #1: {{transferTest|srd|eng|'''Sos''' ki an furatu su dinari at a èssere punitos.|'''The''' people who stole the money will be punished.}}
*:Example #2: {{transferTest|srd|eng|Una de '''sas''' berbekes est maláida.|One of '''the''' sheep is sick.}}

==srd → eng transfer morph tests==
*Diff.1/2, Ex.1:
*: {{transferMorphTest|srd|eng|Su{{tag|det}}{{tag|def}}{{tag|m}}{{tag|sg}} sardu{{tag|n}}{{tag|m}}{{tag|sg}} èssere{{tag|vbser}}{{tag|pri}}{{tag|p3}}{{tag|sg}} unu{{tag|det}}{{tag|ind}}{{tag|f}}{{tag|sg}} limba{{tag|n}}{{tag|f}}{{tag|sg}} anticu{{tag|adj}}{{tag|f}}{{tag|sg}}|Sardinian{{tag|n}}{{tag|sg}} be{{tag|vbser}}{{tag|pres}}{{tag|p3}}{{tag|sg}} a{{tag|det}}{{tag|ind}}{{tag|sg}} ancient{{tag|adj}} language{{tag|n}}{{tag|sg}}}}
*Diff.1/2, Ex.2:
*: {{transferMorphTest|srd|eng|Su{{tag|det}}{{tag|def}}{{tag|f}}{{tag|sg}} Frantza{{tag|np}}{{tag|top}}{{tag|f}}{{tag|sg}} èssere{{tag|vbser}}{{tag|pri}}{{tag|p3}}{{tag|sg}} unu{{tag|det}}{{tag|ind}}{{tag|m}}{{tag|sg}} paisu{{tag|n}}{{tag|m}}{{tag|sg}} bellu{{tag|adj}}{{tag|m}}{{tag|sg}}|France{{tag|np}}{{tag|top}}{{tag|sg}} be{{tag|vbser}}{{tag|pres}}{{tag|p3}}{{tag|sg}} a{{tag|det}}{{tag|ind}}{{tag|sg}} beautiful{{tag|adj}} country{{tag|n}}{{tag|sg}}}}
*Diff.3/5, Ex.1:
*: {{transferMorphTest|srd|eng|àere{{tag|vbhaver}}{{tag|pri}}{{tag|p1}}{{tag|sg}} pèrdere{{tag|vblex}}{{tag|pp}}{{tag|m}}{{tag|sg}} duos{{tag|num}}{{tag|mf}}{{tag|sp}} de{{tag|pr}} su{{tag|det}}{{tag|def}}{{tag|m}}{{tag|pl}} libru{{tag|n}}{{tag|m}}{{tag|pl}} meu{{tag|adj}}{{tag|pos}}{{tag|m}}{{tag|pl}}|prpers{{tag|prn}}{{tag|subj}}{{tag|p1}}{{tag|mf}}{{tag|sg}} have{{tag|vbhaver}}{{tag|pres}} lose{{tag|vblex}}{{tag|pp}} two{{tag|num}}{{tag|pl}} of{{tag|pr}} my{{tag|det}}{{tag|pos}}{{tag|sp}} book{{tag|n}}{{tag|pl}}}}
*Diff.3, Ex.2:
*: {{transferMorphTest|srd|eng|lettu{{tag|n}}{{tag|m}}{{tag|sg}} meu{{tag|adj}}{{tag|pos}}{{tag|m}}{{tag|sg}} èssere{{tag|vbser}}{{tag|pri}}{{tag|p3}}{{tag|sg}}|prpers{{tag|prn}}{{tag|subj}}{{tag|p3}}{{tag|nt}}{{tag|sg}} be{{tag|vbser}}{{tag|pres}}{{tag|p3}}{{tag|sg}} my{{tag|det}}{{tag|pos}}{{tag|sp}} bed{{tag|n}}{{tag|sg}}}}
*Diff.4, Ex.1:
*: {{transferMorphTest|srd|eng|Su{{tag|det}}{{tag|def}}{{tag|m}}{{tag|pl}} chi{{tag|cnjsub}} àere{{tag|vbhaver}}{{tag|pri}}{{tag|p3}}{{tag|pl}} furare{{tag|vblex}}{{tag|pp}}{{tag|m}}{{tag|sg}} su{{tag|det}}{{tag|def}}{{tag|m}}{{tag|sg}} dinari{{tag|n}}{{tag|m}}{{tag|sg}} àere{{tag|vbhaver}}{{tag|pri}}{{tag|p3}}{{tag|sg}} a{{tag|pr}} èssere{{tag|vbser}}{{tag|inf}} punire{{tag|vblex}}{{tag|pp}}{{tag|m}}{{tag|pl}}|the{{tag|det}}{{tag|def}}{{tag|sp}} person{{tag|n}}{{tag|pl}} who{{tag|prn}}{{tag|rel}}{{tag|an}}{{tag|mf}}{{tag|sp}} steal{{tag|vblex}}{{tag|past}} the{{tag|det}}{{tag|def}}{{tag|sp}} money{{tag|n}}{{tag|sg}} will{{tag|vbmod}}{{tag|pres}} be{{tag|vbser}}{{tag|inf}} punish{{tag|vblex}}{{tag|pp}}
*Diff.4, Ex.2:
*: {{transferMorphTest|srd|eng|unu{{tag|prn}}{{tag|tn}}{{tag|f}}{{tag|sg}} de{{tag|pr}} su{{tag|det}}{{tag|def}}{{tag|f}}{{tag|pl}} berbeke{{tag|n}}{{tag|f}}{{tag|pl}} èssere{{tag|vbser}}{{tag|pri}}{{tag|p3}}{{tag|sg}} malàidu{{tag|adj}}{{tag|f}}{{tag|sg}}|one{{tag|prn}}{{tag|dem}}{{tag|mf}}{{tag|sg}} of{{tag|pr}} the{{tag|det}}{{tag|def}}{{tag|sp}} sheep{{tag|n}}{{tag|pl}} be{{tag|vbser}}{{tag|pres}}{{tag|p3}}{{tag|sg}} sick{{tag|adj}}{{tag|sint}}}}
*Diff.5, Ex.2:
*: {{transferMorphTest|srd|eng|Mi{{tag|prn}}{{tag|pro}}{{tag|p1}}{{tag|mf}}{{tag|sg}} àere{{tag|vbhaver}}{{tag|pri}}{{tag|p3}}{{tag|pl}} nàrrere{{tag|vblex}}{{tag|pp}}{{tag|m}}{{tag|sg}} chi{{tag|cnjsub}} su{{tag|det}}{{tag|def}}{{tag|m}}{{tag|sg}} trenu{{tag|n}}{{tag|m}}{{tag|sg}} dèvere{{tag|vblex}}{{tag|pii}}{{tag|p3}}{{tag|sg}} arrivare{{tag|vblex}}{{tag|inf}} a{{tag|pr}} su{{tag|det}}{{tag|def}}{{tag|f}}{{tag|pl}} nove{{tag|num}}{{tag|mf}}{{tag|sg}}|prpers{{tag|prn}}{{tag|subj}}{{tag|p3}}{{tag|mf}}{{tag|pl}} tell{{tag|vblex}}{{tag|past}} prpers{{tag|prn}}{{tag|obj}}{{tag|p1}}{{tag|mf}}{{tag|sg}} that{{tag|cnjsub}} the{{tag|det}}{{tag|def}}{{tag|sp}} train{{tag|n}}{{tag|sg}} be{{tag|vbser}}{{tag|past}}{{tag|p3}}{{tag|sg}} suppose{{tag|vblex}}{{tag|pp}} arrive{{tag|vblex}}{{tag|inf}} at{{tag|pr}} nine{{tag|num}}{{tag|pl}}}}
*Diff.6, Ex.1:
*: {{transferMorphTest|srd|eng|custu{{tag|det}}{{tag|dem}}{{tag|f}}{{tag|sg}} ricu{{tag|n}}{{tag|f}}{{tag|sg}} àere{{tag|vbhaver}}{{tag|pri}}{{tag|p3}}{{tag|sg}} dare{{tag|vblex}}{{tag|pp}}{{tag|m}}{{tag|sg}} milli{{tag|num}}{{tag|mf}}{{tag|sp}} francu{{tag|n}}{{tag|m}}{{tag|pl}} a{{tag|pr}} su{{tag|det}}{{tag|def}}{{tag|m}}{{tag|sg}} betzu{{tag|n}}{{tag|m}}{{tag|sg}}|this{{tag|det}}{{tag|dem}}{{tag|sg}} rich{{tag|adj}}{{tag|sint}} woman{{tag|n}}{{tag|sg}} give{{tag|vblex}}{{tag|past}} a thousand{{tag|num}}{{tag|pl}} franc{{tag|n}}{{tag|pl}} to{{tag|pr}} the{{tag|det}}{{tag|def}}{{tag|sp}} old{{tag|adj}}{{tag|sint}} man{{tag|n}}{{tag|sg}}}}
*Diff.6, Ex.2:
*: {{transferMorphTest|srd|eng|èssere{{tag|vbser}}{{tag|pri}}{{tag|p2}}{{tag|sg}} unu{{tag|det}}{{tag|ind}}{{tag|m}}{{tag|sg}} iscimpru{{tag|n}}{{tag|m}}{{tag|sg}}|prpers{{tag|prn}}{{tag|subj}}{{tag|p2}}{{tag|mf}}{{tag|sp}} be{{tag|vbser}}{{tag|pres}} a{{tag|det}}{{tag|ind}}{{tag|sg}} stupid{{tag|adj}} man{{tag|n}}{{tag|sg}}}}

[[Category:Sp23_ContrastiveGrammars]],[[Category:Sardinian]],[[Category:English]]