LING073 - User contributions [en]

Japhug/Japhug and English

2023-05-10T02:48:56Z

Ylhamo1: /* Monolingual transducer stats */

==Resources for machine translation between [https://wikis.swarthmore.edu/ling073/Category:Japhug Japhug] and English==

===Developed resources===

[https://github.swarthmore.edu/Ling073-sp23/ling073-jya-eng-corpus Japhug-English corpus]

[https://wikis.swarthmore.edu/ling073/Japhug_and_English/Lexical_selection#jya_.E2.86.92_eng Lexical selection]

==External resources==
[https://github.swarthmore.edu/Ling073-sp23/ling073-jya-eng Apertium language pair for translating between Jiarong and English]

[https://github.swarthmore.edu/Ling073-sp23/ling073-jya Monolingual Japhug transducer]

==Jya → Eng evaluation ==

coverage (number of forms analysed) of Japhug transducer on jya.sentences.txt: 76.98 %

coverage of bilingual transducer (jya-eng.automorf.bin) on the same file: 28.61 %

===10 sentences:===

====#1====
The original sentence:
<pre>
kɯɕɯŋgɯ tɕe, nɤki, lɯlu ci pjɤtu, tɕendɤre βʑɯ ci pjɤtu
</pre>
The intended English translation: A long time ago, there was a cat and a mouse

Output of jya-eng-biltrans:
<pre>
^kɯɕɯŋgɯ<n><ind>/long time ago<cnjadv><ind>$ ^tɕe<cnj>//as for<pr>$^,<cm>/,<cm>$ ^nɤki<dem>/that<det><dem><sg>$^,<cm>/,<cm>$ ^lɯlu<n><ind>/cat<n><sg><ind>$ ^ci<det>/a<det><ind><sg>/one<num><sg>$ ^pjɤtu<cop><other>/be<vbser><other>$^,<cm>/,<cm>$ ^tɕendɤre<cnj>/then<cnjadv>$ ^βʑɯ<n><ind>/mouse<n><sg><ind>$ ^ci<det>/a<det><ind><sg>/one<num><sg>$ ^pjɤtu<cop><other>/be<vbser><other>$^.<sent>/.<sent>$
</pre>

Output of jya-eng:
<pre>
#long time ago , that, #cat a #be, then #mouse a #be
</pre>

====#2====
The original sentence:
<pre>
lɯlu nɯ kɯ nɤkinɯ, βʑɯ ri tundze ɕti
</pre>

The intended English translation: The cat ate the mouse,

Output of jya-eng-biltrans:
<pre>
^lɯlu<n><ind>/cat<n><sg><ind>$ ^nɯ<dem>/that<det><dem><sg>$ ^kɯ<post>/with<pr>$ ^nɤkinɯ<fill>/um<ij>$^,<cm>/,<cm>$ ^βʑɯ<n><ind>/mouse<n><sg><ind>$ ^ri<post>/at<pr>$ ^ndze<v><tv><ipfv>/eat<vblex><ipfv>$ ^ɕti<v><iv>/be<vbser>$^.<sent>/.<sent>$
</pre>

Output of jya-eng:
<pre>
#cat that with um, #mouse at #eat #be
</pre>

====#3====
The original sentence:

<pre>
βʑɯ chondɤre nɤki, kumpɣɤtɕɯ nɯ kɯ βzaŋsa tonɯpandʑi,
</pre>

The intended English translation: The mouse made friends with the sparrow,

Output of jya-eng-biltrans:
<pre>
^βʑɯ<n><ind>/mouse<n><sg><ind>$ ^chondɤre<com>/with<pr>$ ^nɤki<dem>/that<det><dem><sg>$^,<cm>/,<cm>$ ^kumpɣɤtɕɯ<n><ind>/sparrow<n><sg><ind>$ ^nɯ<dem>/that<det><dem><sg>$ ^kɯ<post>/with<pr>$ ^βzaŋsa<n><ind>/friend<n><sg><ind>$ ^tonɯpa<v><tv><du>/made<vblex><pp><du>$^,<cm>/,<cm>$^.<sent>/.<sent>$
</pre>

Output of jya-eng:
<pre>
#mouse with that, #sparrow that with #friend #made,
</pre>

====#4====
The original sentence:
<pre>
tɕe βzaŋsa tonɯpandʑi tɕe, wuma pjɤkɤmɯmindʑici
</pre>

The intended English translation: The two of them become friends and got along well

Output of jya-eng-biltrans:
<pre>
^tɕe<cnj>//as for<pr>$ ^βzaŋsa<n><ind>/friend<n><sg><ind>$ ^tonɯpa<v><tv><du>/made<vblex><pp><du>$ ^tɕe<cnj>//as for<pr>$^,<cm>/,<cm>$ ^wuma<adv>/very<adv>$ ^ɤmɯmi<v><iv><pii><du>/get along well<vblex><pii><du>$^.<sent>/.<sent>$</pre>
Output of jya-eng:
<pre>
#friend #made , very #get along well
</pre>

====#5====
The original sentence:
<pre>
maka cici ŋotɕu jɤarɯrindʑi ʑo tɯtɯrca ntsɯ juɕendʑi pjɤŋu
</pre>
The intended English translation: they always got together

Output of jya-eng-biltrans:
<pre>
^maka<adv>/at all<adv>$ ^cici<adv>/sometimes<adv>$ ^ŋotɕu<prn>/wherever<adv>$ ^*jɤarɯrindʑi/*jɤarɯrindʑi$ ^*ʑo/*ʑo$ ^*tɯtɯrca/*tɯtɯrca$ ^ntsɯ<adv>/always<adv>$ ^*juɕendʑi/*juɕendʑi$ ^ŋu<v><iv><pii>/be<vbser><pii>$^.<sent>/.<sent>$
</pre>
Output of jya-eng:
<pre>
at all sometimes wherever #each together always #go #be
</pre>

====#6====
The original sentence:
<pre>
kɤndza ci tu nɤ pjɯnɯkrondʑi
</pre>
The intended English translation: There was food to eat, they shared,

Output of jya-eng-biltrans:
<pre>
^kɤndza<n><ind>/food<n><sg><ind>$ ^ci<det>/a<det><ind><sg>/one<num><sg>$ ^tu<v><iv>/be<vbser>/exist<vblex>$ ^*nɤ/*nɤ$ ^*pjɯnɯkrondʑi/*pjɯnɯkrondʑi$^.<sent>/.<sent>$
</pre>
Output of jya-eng:
<pre>
#food a #be at #share
</pre>

====#7====
The original sentence:
<pre>
nɯ mɤʑɯ kɯmtɕhɯ kɯfse tɤtu nɤ, tɯɣrɤz ɲɯnɤɣrondʑi nɯ ra pjɤŋgrɤl
</pre>

The intended English translation: Also, when there was something to play with, they played together

Output of jya-eng-biltrans:
<pre>
^nɯ<dem>/that<det><dem><sg>$ ^mɤʑɯ<adv>/again<adv>$ ^kɯmtɕhɯ<n><ind>/toy<n><sg><ind>$ ^fse<v><tv><prc><sbj><ind>/resemble<vblex><prc><sbj><ind>$ ^tu<v><iv><aor>/be<vbser><aor>/exist<vblex><aor>$ ^nɤ<post>/at<pr>$^,<cm>/,<cm>$ ^tɯɣrɤz<adv>/together<adv>$ ^nɤɣro<v><tv><ipfv><du>/play<vblex><inf><ipfv><du>$ ^nɯ<dem>/that<det><dem><sg>$ ^ra<v><iv>/should<vbmod>$ ^ŋgrɤl<v><iv><pii>/usually like this<iv><pii>$^.<sent>/.<sent>$
</pre>

Output of jya-eng:
<pre>
that again #toy #resemble #be at, together #play that #should #usually like this
</pre>

====#8====
The original sentence:
<pre>
tɕhi kɤcha tukɤpjɤl kowa ntsɯ tuβzundʑi pjɤŋu tɕe
</pre>

The intended English translation: They were always trying to think of ways to evade that cat

Output of jya-eng-biltrans:
<pre>
^tɕhi<prn>/what<prn>$ ^cha<v><iv><prc><obj><ind>/able<adj><prc><obj><ind>/can<vbmod><prc><obj><ind>$ ^pjɤl<v><tv><inf><ipfv>/evade<vblex><inf><ipfv>$ ^kowa<n><ind>/method<n><sg><ind>$ ^ntsɯ<adv>/always<adv>$ ^βzu<v><tv><ipfv><du>/make<vblex><ipfv><du>$ ^ŋu<v><iv><pii>/be<vbser><pii>$ ^tɕe<cnj>//as for<pr>$^.<sent>/.<sent>$
</pre>

Output of jya-eng:
<pre>
#what #able #evade #method always #make #be
</pre>

====#9====
The original sentence:
<pre>
lɯlu nɯ kɯ βʑɯ ɯɕa tɕi pjɤrga, pɣɤtɕɯ ɯɕa tɕi pjɤrga ɕti tɕe.
</pre>

The intended English translation: The cat likes eating rat meat, and also likes sparrow meat.

Output of jya-eng-biltrans:
<pre>
^lɯlu<n><ind>/cat<n><sg><ind>$ ^nɯ<dem>/that<det><dem><sg>$ ^kɯ<post>/with<pr>$ ^βʑɯ<n><ind>/mouse<n><sg><ind>$ ^ɕa<n><px3sg>/meat<n><sg><px3sg>$ ^tɕi<adv>/also<adv>$ ^rga<v><iv><pii>/like<vblex><pii>$^,<cm>/,<cm>$ ^pɣɤtɕɯ<n><ind>/bird<n><sg><ind>$ ^ɕa<n><px3sg>/meat<n><sg><px3sg>$ ^tɕi<adv>/also<adv>$ ^rga<v><iv><pii>/like<vblex><pii>$ ^ɕti<v><iv>/be<vbser>$ ^tɕe<cnj>//as for<pr>$^.<sent>/.<sent>$^.<sent>/.<sent>$
</pre>

Output of jya-eng:
<pre>
#cat that with #mouse #meat also #like, #bird #meat also #like #be .
</pre>

====#10====
The original sentence:
<pre>
tɕe nɯ maʁ nɤ tɕe, βʑɯ nɯ kɯ wuma kɤrɤfsoʁ pjɤcha tɕe
</pre>

The intended English translation: since then, that mouse was very good at accumulating food

Output of jya-eng-biltrans:
<pre>
^tɕe<cnj>//as for<pr>$ ^nɯ maʁ nɤ<cnj>/or<cnjcoo>$ ^tɕe<cnj>//as for<pr>$^,<cm>/,<cm>$ ^βʑɯ<n><ind>/mouse<n><sg><ind>$ ^nɯ<dem>/that<det><dem><sg>$ ^kɯ<post>/with<pr>$ ^wuma<adv>/very<adv>$ ^rɤfsoʁ<v><iv><prc><obj><ind>/forage<vblex><prc><obj><ind>$ ^cha<v><iv><pii>/able<adj><pii>/can<vbmod><pii>$ ^tɕe<cnj>//as for<pr>$^.<sent>/.<sent>$
</pre>

Output of jya-eng:
<pre>
or , #mouse that with very #forage #able
</pre>

===Additions ===
These are some additions we made to our bilingual transducer beyond the labs.

* 5000+ lemmas to our Japhug transducer

* 5 new features covered in our Japhug morphological analyzer, including: imperfective prefixes, the peg circumfix, proximal/distal demonstratives, redesigned verb patterns to match the slot-based prefix system in Japhug, number suffixes on verbs.

* 2 new structural transfer rules: NP rule to combine nouns and possessed nouns; DP rule to place determiner before noun, and to take ergative case from postposition; vP rule to combine adverbs and verbs. These were made in the process of meeting our original goal, to match the SVO word order in English (Japhug is usually SOV or OSV)

(details listed for our own reference)

===Final evaluation===

====Monolingual transducer stats====
*Updated precision and recall against the (updated) eval.test and eval.gold files:
<pre>
$ precisionRecall jya.eval.test.new.txt jya.eval.gold.txt
Totals: 79 forms, 221 tp, 155 fp, 0 tn, 87 fn
Precision: 58.77660%
Recall: 71.75325%
</pre>
*Coverage over the large corpus:
<pre>
TOP UNKNOWN WORDS:
16 ^ɣɯ/*ɣɯ$
14 ^lɤβzaŋ/*lɤβzaŋ$
11 ^cho/*cho$
10 ^qartshɤs/*qartshɤs$
8 ^rɟɤlpu/*rɟɤlpu$
8 ^rcanɯ/*rcanɯ$
8 ^qhe/*qhe$
8 ^je/*je$
8 ^jamɤn/*jamɤn$
7 ^tɕɤn/*tɕɤn$
6 ^nɯmbala/*nɯmbala$
6 ^ndɤ/*ndɤ$
6 ^lɤari/*lɤari$
6 ^kɯki/*kɯki$
5 ^wo/*wo$
5 ^tɯɣjɤn/*tɯɣjɤn$
5 ^lɤɣe/*lɤɣe$
5 ^kɯsthɯci/*kɯsthɯci$
5 ^ciŋglɯɣ/*ciŋglɯɣ$
4 ^ɲɯsɯsɤm/*ɲɯsɯsɤm$
coverage: 4463 / 5019 (~0.88922096035066746364)
remaining unknown forms: 556
ambiguity: 9939 / 5019 (~1.98027495517035265989)
jya.corpus Mon May 8 02:13:49 PM EDT 2023 4463/5019 ~0.88922096035066746364 \| 9939/5019 ~1.98027495517035265989
</pre>
*The number of words in the large corpus: 3999
*The number of stems in the transducer: 6646

====MT in jya-eng stats====
*WER and PER over longer corpus:

<pre>
Statistics about input files
-------------------------------------------------------
Number of words in reference: 3013
Number of words in test: 2450
Number of unknown words (marked with a star) in test: 996
Percentage of unknown words: 40.65 %

Results when removing unknown-word marks (stars)
-------------------------------------------------------
Edit distance: 3116
Word error rate (WER): 103.42 %
Number of position-independent correct words: 85
Position-independent word error rate (PER): 97.18 %
</pre>
*The proportion of stems translated correctly in the longer corpus: 100% - 103.42% = -3.42%
*Trimmed coverage over longer corpora: ~0.68006279434850863422
*Trimmed coverage over large corpora: ~0.63545647558386411890
*The number of tokens in longer corpora: 3185
*The number of tokens in large corpora: 4710

[[Category:Sp23_TranslationPairs ]] [[Category: Japhug]]

Japhug/Japhug and English

2023-05-10T02:48:37Z

Ylhamo1: /* MT in jya-eng stats */

==Resources for machine translation between [https://wikis.swarthmore.edu/ling073/Category:Japhug Japhug] and English==

===Developed resources===

[https://github.swarthmore.edu/Ling073-sp23/ling073-jya-eng-corpus Japhug-English corpus]

[https://wikis.swarthmore.edu/ling073/Japhug_and_English/Lexical_selection#jya_.E2.86.92_eng Lexical selection]

==External resources==
[https://github.swarthmore.edu/Ling073-sp23/ling073-jya-eng Apertium language pair for translating between Jiarong and English]

[https://github.swarthmore.edu/Ling073-sp23/ling073-jya Monolingual Japhug transducer]

==Jya → Eng evaluation ==

coverage (number of forms analysed) of Japhug transducer on jya.sentences.txt: 76.98 %

coverage of bilingual transducer (jya-eng.automorf.bin) on the same file: 28.61 %

===10 sentences:===

====#1====
The original sentence:
<pre>
kɯɕɯŋgɯ tɕe, nɤki, lɯlu ci pjɤtu, tɕendɤre βʑɯ ci pjɤtu
</pre>
The intended English translation: A long time ago, there was a cat and a mouse

Output of jya-eng-biltrans:
<pre>
^kɯɕɯŋgɯ<n><ind>/long time ago<cnjadv><ind>$ ^tɕe<cnj>//as for<pr>$^,<cm>/,<cm>$ ^nɤki<dem>/that<det><dem><sg>$^,<cm>/,<cm>$ ^lɯlu<n><ind>/cat<n><sg><ind>$ ^ci<det>/a<det><ind><sg>/one<num><sg>$ ^pjɤtu<cop><other>/be<vbser><other>$^,<cm>/,<cm>$ ^tɕendɤre<cnj>/then<cnjadv>$ ^βʑɯ<n><ind>/mouse<n><sg><ind>$ ^ci<det>/a<det><ind><sg>/one<num><sg>$ ^pjɤtu<cop><other>/be<vbser><other>$^.<sent>/.<sent>$
</pre>

Output of jya-eng:
<pre>
#long time ago , that, #cat a #be, then #mouse a #be
</pre>

====#2====
The original sentence:
<pre>
lɯlu nɯ kɯ nɤkinɯ, βʑɯ ri tundze ɕti
</pre>

The intended English translation: The cat ate the mouse,

Output of jya-eng-biltrans:
<pre>
^lɯlu<n><ind>/cat<n><sg><ind>$ ^nɯ<dem>/that<det><dem><sg>$ ^kɯ<post>/with<pr>$ ^nɤkinɯ<fill>/um<ij>$^,<cm>/,<cm>$ ^βʑɯ<n><ind>/mouse<n><sg><ind>$ ^ri<post>/at<pr>$ ^ndze<v><tv><ipfv>/eat<vblex><ipfv>$ ^ɕti<v><iv>/be<vbser>$^.<sent>/.<sent>$
</pre>

Output of jya-eng:
<pre>
#cat that with um, #mouse at #eat #be
</pre>

====#3====
The original sentence:

<pre>
βʑɯ chondɤre nɤki, kumpɣɤtɕɯ nɯ kɯ βzaŋsa tonɯpandʑi,
</pre>

The intended English translation: The mouse made friends with the sparrow,

Output of jya-eng-biltrans:
<pre>
^βʑɯ<n><ind>/mouse<n><sg><ind>$ ^chondɤre<com>/with<pr>$ ^nɤki<dem>/that<det><dem><sg>$^,<cm>/,<cm>$ ^kumpɣɤtɕɯ<n><ind>/sparrow<n><sg><ind>$ ^nɯ<dem>/that<det><dem><sg>$ ^kɯ<post>/with<pr>$ ^βzaŋsa<n><ind>/friend<n><sg><ind>$ ^tonɯpa<v><tv><du>/made<vblex><pp><du>$^,<cm>/,<cm>$^.<sent>/.<sent>$
</pre>

Output of jya-eng:
<pre>
#mouse with that, #sparrow that with #friend #made,
</pre>

====#4====
The original sentence:
<pre>
tɕe βzaŋsa tonɯpandʑi tɕe, wuma pjɤkɤmɯmindʑici
</pre>

The intended English translation: The two of them become friends and got along well

Output of jya-eng-biltrans:
<pre>
^tɕe<cnj>//as for<pr>$ ^βzaŋsa<n><ind>/friend<n><sg><ind>$ ^tonɯpa<v><tv><du>/made<vblex><pp><du>$ ^tɕe<cnj>//as for<pr>$^,<cm>/,<cm>$ ^wuma<adv>/very<adv>$ ^ɤmɯmi<v><iv><pii><du>/get along well<vblex><pii><du>$^.<sent>/.<sent>$</pre>
Output of jya-eng:
<pre>
#friend #made , very #get along well
</pre>

====#5====
The original sentence:
<pre>
maka cici ŋotɕu jɤarɯrindʑi ʑo tɯtɯrca ntsɯ juɕendʑi pjɤŋu
</pre>
The intended English translation: they always got together

Output of jya-eng-biltrans:
<pre>
^maka<adv>/at all<adv>$ ^cici<adv>/sometimes<adv>$ ^ŋotɕu<prn>/wherever<adv>$ ^*jɤarɯrindʑi/*jɤarɯrindʑi$ ^*ʑo/*ʑo$ ^*tɯtɯrca/*tɯtɯrca$ ^ntsɯ<adv>/always<adv>$ ^*juɕendʑi/*juɕendʑi$ ^ŋu<v><iv><pii>/be<vbser><pii>$^.<sent>/.<sent>$
</pre>
Output of jya-eng:
<pre>
at all sometimes wherever #each together always #go #be
</pre>

====#6====
The original sentence:
<pre>
kɤndza ci tu nɤ pjɯnɯkrondʑi
</pre>
The intended English translation: There was food to eat, they shared,

Output of jya-eng-biltrans:
<pre>
^kɤndza<n><ind>/food<n><sg><ind>$ ^ci<det>/a<det><ind><sg>/one<num><sg>$ ^tu<v><iv>/be<vbser>/exist<vblex>$ ^*nɤ/*nɤ$ ^*pjɯnɯkrondʑi/*pjɯnɯkrondʑi$^.<sent>/.<sent>$
</pre>
Output of jya-eng:
<pre>
#food a #be at #share
</pre>

====#7====
The original sentence:
<pre>
nɯ mɤʑɯ kɯmtɕhɯ kɯfse tɤtu nɤ, tɯɣrɤz ɲɯnɤɣrondʑi nɯ ra pjɤŋgrɤl
</pre>

The intended English translation: Also, when there was something to play with, they played together

Output of jya-eng-biltrans:
<pre>
^nɯ<dem>/that<det><dem><sg>$ ^mɤʑɯ<adv>/again<adv>$ ^kɯmtɕhɯ<n><ind>/toy<n><sg><ind>$ ^fse<v><tv><prc><sbj><ind>/resemble<vblex><prc><sbj><ind>$ ^tu<v><iv><aor>/be<vbser><aor>/exist<vblex><aor>$ ^nɤ<post>/at<pr>$^,<cm>/,<cm>$ ^tɯɣrɤz<adv>/together<adv>$ ^nɤɣro<v><tv><ipfv><du>/play<vblex><inf><ipfv><du>$ ^nɯ<dem>/that<det><dem><sg>$ ^ra<v><iv>/should<vbmod>$ ^ŋgrɤl<v><iv><pii>/usually like this<iv><pii>$^.<sent>/.<sent>$
</pre>

Output of jya-eng:
<pre>
that again #toy #resemble #be at, together #play that #should #usually like this
</pre>

====#8====
The original sentence:
<pre>
tɕhi kɤcha tukɤpjɤl kowa ntsɯ tuβzundʑi pjɤŋu tɕe
</pre>

The intended English translation: They were always trying to think of ways to evade that cat

Output of jya-eng-biltrans:
<pre>
^tɕhi<prn>/what<prn>$ ^cha<v><iv><prc><obj><ind>/able<adj><prc><obj><ind>/can<vbmod><prc><obj><ind>$ ^pjɤl<v><tv><inf><ipfv>/evade<vblex><inf><ipfv>$ ^kowa<n><ind>/method<n><sg><ind>$ ^ntsɯ<adv>/always<adv>$ ^βzu<v><tv><ipfv><du>/make<vblex><ipfv><du>$ ^ŋu<v><iv><pii>/be<vbser><pii>$ ^tɕe<cnj>//as for<pr>$^.<sent>/.<sent>$
</pre>

Output of jya-eng:
<pre>
#what #able #evade #method always #make #be
</pre>

====#9====
The original sentence:
<pre>
lɯlu nɯ kɯ βʑɯ ɯɕa tɕi pjɤrga, pɣɤtɕɯ ɯɕa tɕi pjɤrga ɕti tɕe.
</pre>

The intended English translation: The cat likes eating rat meat, and also likes sparrow meat.

Output of jya-eng-biltrans:
<pre>
^lɯlu<n><ind>/cat<n><sg><ind>$ ^nɯ<dem>/that<det><dem><sg>$ ^kɯ<post>/with<pr>$ ^βʑɯ<n><ind>/mouse<n><sg><ind>$ ^ɕa<n><px3sg>/meat<n><sg><px3sg>$ ^tɕi<adv>/also<adv>$ ^rga<v><iv><pii>/like<vblex><pii>$^,<cm>/,<cm>$ ^pɣɤtɕɯ<n><ind>/bird<n><sg><ind>$ ^ɕa<n><px3sg>/meat<n><sg><px3sg>$ ^tɕi<adv>/also<adv>$ ^rga<v><iv><pii>/like<vblex><pii>$ ^ɕti<v><iv>/be<vbser>$ ^tɕe<cnj>//as for<pr>$^.<sent>/.<sent>$^.<sent>/.<sent>$
</pre>

Output of jya-eng:
<pre>
#cat that with #mouse #meat also #like, #bird #meat also #like #be .
</pre>

====#10====
The original sentence:
<pre>
tɕe nɯ maʁ nɤ tɕe, βʑɯ nɯ kɯ wuma kɤrɤfsoʁ pjɤcha tɕe
</pre>

The intended English translation: since then, that mouse was very good at accumulating food

Output of jya-eng-biltrans:
<pre>
^tɕe<cnj>//as for<pr>$ ^nɯ maʁ nɤ<cnj>/or<cnjcoo>$ ^tɕe<cnj>//as for<pr>$^,<cm>/,<cm>$ ^βʑɯ<n><ind>/mouse<n><sg><ind>$ ^nɯ<dem>/that<det><dem><sg>$ ^kɯ<post>/with<pr>$ ^wuma<adv>/very<adv>$ ^rɤfsoʁ<v><iv><prc><obj><ind>/forage<vblex><prc><obj><ind>$ ^cha<v><iv><pii>/able<adj><pii>/can<vbmod><pii>$ ^tɕe<cnj>//as for<pr>$^.<sent>/.<sent>$
</pre>

Output of jya-eng:
<pre>
or , #mouse that with very #forage #able
</pre>

===Additions ===
These are some additions we made to our bilingual transducer beyond the labs.

* 5000+ lemmas to our Japhug transducer

* 5 new features covered in our Japhug morphological analyzer, including: imperfective prefixes, the peg circumfix, proximal/distal demonstratives, redesigned verb patterns to match the slot-based prefix system in Japhug, number suffixes on verbs.

* 2 new structural transfer rules: NP rule to combine nouns and possessed nouns; DP rule to place determiner before noun, and to take ergative case from postposition; vP rule to combine adverbs and verbs. These were made in the process of meeting our original goal, to match the SVO word order in English (Japhug is usually SOV or OSV)

(details listed for our own reference)

===Final evaluation===

====Monolingual transducer stats====
*Updated precision and recall against the (updated) eval.test and eval.gold files:
<pre>
$ precisionRecall jya.eval.test.new.txt jya.eval.gold.txt
Totals: 79 forms, 221 tp, 155 fp, 0 tn, 87 fn
Precision: 58.77660%
Recall: 71.75325%
</pre>
*Coverage over the large corpus:
<pre>
TOP UNKNOWN WORDS:
16 ^ɣɯ/*ɣɯ$
14 ^lɤβzaŋ/*lɤβzaŋ$
11 ^cho/*cho$
10 ^qartshɤs/*qartshɤs$
8 ^rɟɤlpu/*rɟɤlpu$
8 ^rcanɯ/*rcanɯ$
8 ^qhe/*qhe$
8 ^je/*je$
8 ^jamɤn/*jamɤn$
7 ^tɕɤn/*tɕɤn$
6 ^nɯmbala/*nɯmbala$
6 ^ndɤ/*ndɤ$
6 ^lɤari/*lɤari$
6 ^kɯki/*kɯki$
5 ^wo/*wo$
5 ^tɯɣjɤn/*tɯɣjɤn$
5 ^lɤɣe/*lɤɣe$
5 ^kɯsthɯci/*kɯsthɯci$
5 ^ciŋglɯɣ/*ciŋglɯɣ$
4 ^ɲɯsɯsɤm/*ɲɯsɯsɤm$
coverage: 4463 / 5019 (~0.88922096035066746364)
remaining unknown forms: 556
ambiguity: 9939 / 5019 (~1.98027495517035265989)
jya.corpus Mon May 8 02:13:49 PM EDT 2023 4463/5019 ~0.88922096035066746364 \| 9939/5019 ~1.98027495517035265989
</pre>
*The number of words in the large corpus: 3999
*The number of stems in the transducer): 6646

====MT in jya-eng stats====
*WER and PER over longer corpus:

<pre>
Statistics about input files
-------------------------------------------------------
Number of words in reference: 3013
Number of words in test: 2450
Number of unknown words (marked with a star) in test: 996
Percentage of unknown words: 40.65 %

Results when removing unknown-word marks (stars)
-------------------------------------------------------
Edit distance: 3116
Word error rate (WER): 103.42 %
Number of position-independent correct words: 85
Position-independent word error rate (PER): 97.18 %
</pre>
*The proportion of stems translated correctly in the longer corpus: 100% - 103.42% = -3.42%
*Trimmed coverage over longer corpora: ~0.68006279434850863422
*Trimmed coverage over large corpora: ~0.63545647558386411890
*The number of tokens in longer corpora: 3185
*The number of tokens in large corpora: 4710

[[Category:Sp23_TranslationPairs ]] [[Category: Japhug]]

Japhug/Transducer

2023-05-08T23:36:45Z

Ylhamo1:

Git page for our [https://github.swarthmore.edu/Ling073-sp23/ling073-jya Japhug transducer].

Git page for our [https://github.swarthmore.edu/Ling073-sp23/ling073-jya-corpus corpus].

[https://wikis.swarthmore.edu/ling073/Category:Japhug Wiki page] to the list of resources.
=Analyser evaluation=

==Evaluation==

===Total number of stems in transducer===
<pre>
Lexicons: 22
Lexicon entries: 99
Patterns: 10
Pattern entries: 22

Counts for individual lexicons:
Punctuation: 22
V-Negative: 2
N-Possessive: 12
V-Participles: 3
V-Stems: 21
V-Transitivity: 2
V-Causative: 1
V-Reflexive: 1
V-Passive: 1
N-Stems: 13
N-Collective: 1
Gender: 2
Numeral: 10
All anonymous lexicons: 8
</pre>

===Current coverage===

Updated on Mar 20, 2023
We wrote a script and obtained over 6000 word roots from the Japhug dictionary by Guillaume Jacques [https://hal.inria.fr/halshs-01244860/]
As we added the roots to the lexd file, the coverage becomes nearly 75%.

<pre>
coverage: 2500 / 3341 (~0.74827895839568991320)
remaining unknown forms: 841
ambiguity: 3924 / 3341 (~1.17449865309787488776)

</pre>

===The current list of top unknown words returned by aq-covtest===
<pre>
TOP UNKNOWN WORDS:
27 ^pɣɤtɕɯ/*pɣɤtɕɯ$
10 ^tɕu/*tɕu$
8 ^rɟɤlpu/*rɟɤlpu$
8 ^rcanɯ/*rcanɯ$
7 ^ɯrkɯ/*ɯrkɯ$
7 ^tɤwa/*tɤwa$
7 ^tɤsno/*tɤsno$
7 ^tɕɤn/*tɕɤn$
7 ^ki/*ki$
6 ^ɯpi/*ɯpi$
6 ^ɣɯ/*ɣɯ$
6 ^tɤtɕɯ/*tɤtɕɯ$
6 ^qhe/*qhe$
6 ^pɯme/*pɯme$
6 ^pjɤɕti/*pjɤɕti$
6 ^pjɤŋu/*pjɤŋu$
5 ^ɯloʁ/*ɯloʁ$
5 ^tɯɣjɤn/*tɯɣjɤn$
5 ^tonɯrdoʁ/*tonɯrdoʁ$
5 ^pɯŋu/*pɯŋu$
</pre>

==Notes==
'''Tests that completely fail: '''

*analysis and generation (Irrelevant tests- they are the "house/houses" example by Jonathan)

*Reduplicated Collective-gen and morph (we avoided reduplication and sandhi for this lab)

*Gerund-gen and morph (gerund contains partial reduplication, so we didn't code it)

*Sigmatic Causative-gen (0/11 test match gold)

'''Tests that partially fail''' (We need to check that we're able to generate all the gold standards in our terminal. Not sure why tests below failing):

*Possessive prefixes on nouns-gen (2/25 test not passing) and morph (2/20 test not passing)

*Negation on Verbs-gen (2/4 test do not match gold)

*Sigmatic Causative-morph (2/11 test match gold)

*Passive-morph (1/3 test not passing)

'''Additional top word(s) added: '''
*lɯlu (We already have lɯlu as 'lɯlu:lɯlɤ', the right part is the sandhi. But to improve coverage, we added 'lɯlu:lɯlu')

*βʑɯ ("mouse")

*tɕendɤre ("then")

*ɕti (affirmative "be")

'''Resulting change in coverage:'''

Coverage went from 24.23% to 31.26%

=Generator evaluation=

==Initial evaluation of morphological generation==

''includes commonwords, excludes first two irreverent tests''

number of passing morphological analysis tests: 16

number of failing morphological analysis tests: 5

number of gold matches for the generation test: 43

'''Current coverage''': 31.26%

==Final evaluation of morphological generation==

number of passing morphological analysis tests: 17

number of failing morphological analysis tests: 4

number of twol rules that you added: 6

'''New coverage number''': 31.26%

==Precision and Recall==

Precision: 100% (so 100% of the returned analyses were correct)

Recall: 65.09% (only 65.09% of the correct analyses were returned)

We ran <code>precisionRecall jya.eval.test.txt jya.eval.gold.txt</code>.

[[Category:Sp23_Transducers]][[Category:Japhug]][[Category:Transducers]]

Japhug/Japhug and English

2023-05-08T23:07:59Z

Ylhamo1: /* Final evaluation */

==Resources for machine translation between [https://wikis.swarthmore.edu/ling073/Category:Japhug Japhug] and English==

===Developed resources===

[https://github.swarthmore.edu/Ling073-sp23/ling073-jya-eng-corpus Japhug-English corpus]

[https://wikis.swarthmore.edu/ling073/Japhug_and_English/Lexical_selection#jya_.E2.86.92_eng Lexical selection]

==External resources==
[https://github.swarthmore.edu/Ling073-sp23/ling073-jya-eng Apertium language pair for translating between Jiarong and English]

[https://github.swarthmore.edu/Ling073-sp23/ling073-jya Monolingual Japhug transducer]

==Jya → Eng evaluation ==

coverage (number of forms analysed) of Japhug transducer on jya.sentences.txt: 76.98 %

coverage of bilingual transducer (jya-eng.automorf.bin) on the same file: 28.61 %

===10 sentences:===

====#1====
The original sentence:
<pre>
kɯɕɯŋgɯ tɕe, nɤki, lɯlu ci pjɤtu, tɕendɤre βʑɯ ci pjɤtu
</pre>
The intended English translation: A long time ago, there was a cat and a mouse

Output of jya-eng-biltrans:
<pre>
^kɯɕɯŋgɯ<n><ind>/long time ago<cnjadv><ind>$ ^tɕe<cnj>//as for<pr>$^,<cm>/,<cm>$ ^nɤki<dem>/that<det><dem><sg>$^,<cm>/,<cm>$ ^lɯlu<n><ind>/cat<n><sg><ind>$ ^ci<det>/a<det><ind><sg>/one<num><sg>$ ^pjɤtu<cop><other>/be<vbser><other>$^,<cm>/,<cm>$ ^tɕendɤre<cnj>/then<cnjadv>$ ^βʑɯ<n><ind>/mouse<n><sg><ind>$ ^ci<det>/a<det><ind><sg>/one<num><sg>$ ^pjɤtu<cop><other>/be<vbser><other>$^.<sent>/.<sent>$
</pre>

Output of jya-eng:
<pre>
#long time ago , that, #cat a #be, then #mouse a #be
</pre>

====#2====
The original sentence:
<pre>
lɯlu nɯ kɯ nɤkinɯ, βʑɯ ri tundze ɕti
</pre>

The intended English translation: The cat ate the mouse,

Output of jya-eng-biltrans:
<pre>
^lɯlu<n><ind>/cat<n><sg><ind>$ ^nɯ<dem>/that<det><dem><sg>$ ^kɯ<post>/with<pr>$ ^nɤkinɯ<fill>/um<ij>$^,<cm>/,<cm>$ ^βʑɯ<n><ind>/mouse<n><sg><ind>$ ^ri<post>/at<pr>$ ^ndze<v><tv><ipfv>/eat<vblex><ipfv>$ ^ɕti<v><iv>/be<vbser>$^.<sent>/.<sent>$
</pre>

Output of jya-eng:
<pre>
#cat that with um, #mouse at #eat #be
</pre>

====#3====
The original sentence:

<pre>
βʑɯ chondɤre nɤki, kumpɣɤtɕɯ nɯ kɯ βzaŋsa tonɯpandʑi,
</pre>

The intended English translation: The mouse made friends with the sparrow,

Output of jya-eng-biltrans:
<pre>
^βʑɯ<n><ind>/mouse<n><sg><ind>$ ^chondɤre<com>/with<pr>$ ^nɤki<dem>/that<det><dem><sg>$^,<cm>/,<cm>$ ^kumpɣɤtɕɯ<n><ind>/sparrow<n><sg><ind>$ ^nɯ<dem>/that<det><dem><sg>$ ^kɯ<post>/with<pr>$ ^βzaŋsa<n><ind>/friend<n><sg><ind>$ ^tonɯpa<v><tv><du>/made<vblex><pp><du>$^,<cm>/,<cm>$^.<sent>/.<sent>$
</pre>

Output of jya-eng:
<pre>
#mouse with that, #sparrow that with #friend #made,
</pre>

====#4====
The original sentence:
<pre>
tɕe βzaŋsa tonɯpandʑi tɕe, wuma pjɤkɤmɯmindʑici
</pre>

The intended English translation: The two of them become friends and got along well

Output of jya-eng-biltrans:
<pre>
^tɕe<cnj>//as for<pr>$ ^βzaŋsa<n><ind>/friend<n><sg><ind>$ ^tonɯpa<v><tv><du>/made<vblex><pp><du>$ ^tɕe<cnj>//as for<pr>$^,<cm>/,<cm>$ ^wuma<adv>/very<adv>$ ^ɤmɯmi<v><iv><pii><du>/get along well<vblex><pii><du>$^.<sent>/.<sent>$</pre>
Output of jya-eng:
<pre>
#friend #made , very #get along well
</pre>

====#5====
The original sentence:
<pre>
maka cici ŋotɕu jɤarɯrindʑi ʑo tɯtɯrca ntsɯ juɕendʑi pjɤŋu
</pre>
The intended English translation: they always got together

Output of jya-eng-biltrans:
<pre>
^maka<adv>/at all<adv>$ ^cici<adv>/sometimes<adv>$ ^ŋotɕu<prn>/wherever<adv>$ ^*jɤarɯrindʑi/*jɤarɯrindʑi$ ^*ʑo/*ʑo$ ^*tɯtɯrca/*tɯtɯrca$ ^ntsɯ<adv>/always<adv>$ ^*juɕendʑi/*juɕendʑi$ ^ŋu<v><iv><pii>/be<vbser><pii>$^.<sent>/.<sent>$
</pre>
Output of jya-eng:
<pre>
at all sometimes wherever #each together always #go #be
</pre>

====#6====
The original sentence:
<pre>
kɤndza ci tu nɤ pjɯnɯkrondʑi
</pre>
The intended English translation: There was food to eat, they shared,

Output of jya-eng-biltrans:
<pre>
^kɤndza<n><ind>/food<n><sg><ind>$ ^ci<det>/a<det><ind><sg>/one<num><sg>$ ^tu<v><iv>/be<vbser>/exist<vblex>$ ^*nɤ/*nɤ$ ^*pjɯnɯkrondʑi/*pjɯnɯkrondʑi$^.<sent>/.<sent>$
</pre>
Output of jya-eng:
<pre>
#food a #be at #share
</pre>

====#7====
The original sentence:
<pre>
nɯ mɤʑɯ kɯmtɕhɯ kɯfse tɤtu nɤ, tɯɣrɤz ɲɯnɤɣrondʑi nɯ ra pjɤŋgrɤl
</pre>

The intended English translation: Also, when there was something to play with, they played together

Output of jya-eng-biltrans:
<pre>
^nɯ<dem>/that<det><dem><sg>$ ^mɤʑɯ<adv>/again<adv>$ ^kɯmtɕhɯ<n><ind>/toy<n><sg><ind>$ ^fse<v><tv><prc><sbj><ind>/resemble<vblex><prc><sbj><ind>$ ^tu<v><iv><aor>/be<vbser><aor>/exist<vblex><aor>$ ^nɤ<post>/at<pr>$^,<cm>/,<cm>$ ^tɯɣrɤz<adv>/together<adv>$ ^nɤɣro<v><tv><ipfv><du>/play<vblex><inf><ipfv><du>$ ^nɯ<dem>/that<det><dem><sg>$ ^ra<v><iv>/should<vbmod>$ ^ŋgrɤl<v><iv><pii>/usually like this<iv><pii>$^.<sent>/.<sent>$
</pre>

Output of jya-eng:
<pre>
that again #toy #resemble #be at, together #play that #should #usually like this
</pre>

====#8====
The original sentence:
<pre>
tɕhi kɤcha tukɤpjɤl kowa ntsɯ tuβzundʑi pjɤŋu tɕe
</pre>

The intended English translation: They were always trying to think of ways to evade that cat

Output of jya-eng-biltrans:
<pre>
^tɕhi<prn>/what<prn>$ ^cha<v><iv><prc><obj><ind>/able<adj><prc><obj><ind>/can<vbmod><prc><obj><ind>$ ^pjɤl<v><tv><inf><ipfv>/evade<vblex><inf><ipfv>$ ^kowa<n><ind>/method<n><sg><ind>$ ^ntsɯ<adv>/always<adv>$ ^βzu<v><tv><ipfv><du>/make<vblex><ipfv><du>$ ^ŋu<v><iv><pii>/be<vbser><pii>$ ^tɕe<cnj>//as for<pr>$^.<sent>/.<sent>$
</pre>

Output of jya-eng:
<pre>
#what #able #evade #method always #make #be
</pre>

====#9====
The original sentence:
<pre>
lɯlu nɯ kɯ βʑɯ ɯɕa tɕi pjɤrga, pɣɤtɕɯ ɯɕa tɕi pjɤrga ɕti tɕe.
</pre>

The intended English translation: The cat likes eating rat meat, and also likes sparrow meat.

Output of jya-eng-biltrans:
<pre>
^lɯlu<n><ind>/cat<n><sg><ind>$ ^nɯ<dem>/that<det><dem><sg>$ ^kɯ<post>/with<pr>$ ^βʑɯ<n><ind>/mouse<n><sg><ind>$ ^ɕa<n><px3sg>/meat<n><sg><px3sg>$ ^tɕi<adv>/also<adv>$ ^rga<v><iv><pii>/like<vblex><pii>$^,<cm>/,<cm>$ ^pɣɤtɕɯ<n><ind>/bird<n><sg><ind>$ ^ɕa<n><px3sg>/meat<n><sg><px3sg>$ ^tɕi<adv>/also<adv>$ ^rga<v><iv><pii>/like<vblex><pii>$ ^ɕti<v><iv>/be<vbser>$ ^tɕe<cnj>//as for<pr>$^.<sent>/.<sent>$^.<sent>/.<sent>$
</pre>

Output of jya-eng:
<pre>
#cat that with #mouse #meat also #like, #bird #meat also #like #be .
</pre>

====#10====
The original sentence:
<pre>
tɕe nɯ maʁ nɤ tɕe, βʑɯ nɯ kɯ wuma kɤrɤfsoʁ pjɤcha tɕe
</pre>

The intended English translation: since then, that mouse was very good at accumulating food

Output of jya-eng-biltrans:
<pre>
^tɕe<cnj>//as for<pr>$ ^nɯ maʁ nɤ<cnj>/or<cnjcoo>$ ^tɕe<cnj>//as for<pr>$^,<cm>/,<cm>$ ^βʑɯ<n><ind>/mouse<n><sg><ind>$ ^nɯ<dem>/that<det><dem><sg>$ ^kɯ<post>/with<pr>$ ^wuma<adv>/very<adv>$ ^rɤfsoʁ<v><iv><prc><obj><ind>/forage<vblex><prc><obj><ind>$ ^cha<v><iv><pii>/able<adj><pii>/can<vbmod><pii>$ ^tɕe<cnj>//as for<pr>$^.<sent>/.<sent>$
</pre>

Output of jya-eng:
<pre>
or , #mouse that with very #forage #able
</pre>

===Additions ===
These are some additions we made to our bilingual transducer beyond the labs.

* 5000+ lemmas to our Japhug transducer

* 5 new features covered in our Japhug morphological analyzer, including: imperfective prefixes, the peg circumfix, proximal/distal demonstratives, redesigned verb patterns to match the slot-based prefix system in Japhug, number suffixes on verbs.

* 2 new structural transfer rules: NP rule to combine nouns and possessed nouns; DP rule to place determiner before noun, and to take ergative case from postposition; vP rule to combine adverbs and verbs. These were made in the process of meeting our original goal, to match the SVO word order in English (Japhug is usually SOV or OSV)

(details listed for our own reference)

===Final evaluation===

====Monolingual transducer stats====
*Updated precision and recall against the (updated) eval.test and eval.gold files:
<pre>
$ precisionRecall jya.eval.test.new.txt jya.eval.gold.txt
Totals: 79 forms, 221 tp, 155 fp, 0 tn, 87 fn
Precision: 58.77660%
Recall: 71.75325%
</pre>
*Coverage over the large corpus:
<pre>
TOP UNKNOWN WORDS:
16 ^ɣɯ/*ɣɯ$
14 ^lɤβzaŋ/*lɤβzaŋ$
11 ^cho/*cho$
10 ^qartshɤs/*qartshɤs$
8 ^rɟɤlpu/*rɟɤlpu$
8 ^rcanɯ/*rcanɯ$
8 ^qhe/*qhe$
8 ^je/*je$
8 ^jamɤn/*jamɤn$
7 ^tɕɤn/*tɕɤn$
6 ^nɯmbala/*nɯmbala$
6 ^ndɤ/*ndɤ$
6 ^lɤari/*lɤari$
6 ^kɯki/*kɯki$
5 ^wo/*wo$
5 ^tɯɣjɤn/*tɯɣjɤn$
5 ^lɤɣe/*lɤɣe$
5 ^kɯsthɯci/*kɯsthɯci$
5 ^ciŋglɯɣ/*ciŋglɯɣ$
4 ^ɲɯsɯsɤm/*ɲɯsɯsɤm$
coverage: 4463 / 5019 (~0.88922096035066746364)
remaining unknown forms: 556
ambiguity: 9939 / 5019 (~1.98027495517035265989)
jya.corpus Mon May 8 02:13:49 PM EDT 2023 4463/5019 ~0.88922096035066746364 \| 9939/5019 ~1.98027495517035265989
</pre>
*The number of words in the large corpus: 3999
*The number of stems in the transducer): 6646

====MT in jya-eng stats====
*WER and PER over longer corpus:

<pre>
Statistics about input files
-------------------------------------------------------
Number of words in reference: 3013
Number of words in test: 2444
Number of unknown words (marked with a star) in test: 1243
Percentage of unknown words: 50.86 %

Results when removing unknown-word marks (stars)
-------------------------------------------------------
Edit distance: 3138
Word error rate (WER): 104.15 %
Number of position-independent correct words: 57
Position-independent word error rate (PER): 98.11 %
</pre>
*The proportion of stems translated correctly in the longer corpus: 100- 50.86 = 49.14%
*Trimmed coverage over longer corpora: ~0.90917159763313609467
*Trimmed coverage over large corpora: ~0.88922096035066746364
*The number of tokens in longer corpora: 307
*The number of tokens in large corpora: 556

[[Category:Sp23_TranslationPairs ]] [[Category: Japhug]]

Japhug/Japhug and English

2023-05-08T23:00:36Z

Ylhamo1: /* Final evaluation */

==Resources for machine translation between [https://wikis.swarthmore.edu/ling073/Category:Japhug Japhug] and English==

===Developed resources===

[https://github.swarthmore.edu/Ling073-sp23/ling073-jya-eng-corpus Japhug-English corpus]

[https://wikis.swarthmore.edu/ling073/Japhug_and_English/Lexical_selection#jya_.E2.86.92_eng Lexical selection]

==External resources==
[https://github.swarthmore.edu/Ling073-sp23/ling073-jya-eng Apertium language pair for translating between Jiarong and English]

[https://github.swarthmore.edu/Ling073-sp23/ling073-jya Monolingual Japhug transducer]

==Jya → Eng evaluation ==

coverage (number of forms analysed) of Japhug transducer on jya.sentences.txt: 76.98 %

coverage of bilingual transducer (jya-eng.automorf.bin) on the same file: 28.61 %

===10 sentences:===

====#1====
The original sentence:
<pre>
kɯɕɯŋgɯ tɕe, nɤki, lɯlu ci pjɤtu, tɕendɤre βʑɯ ci pjɤtu
</pre>
The intended English translation: A long time ago, there was a cat and a mouse

Output of jya-eng-biltrans:
<pre>
^kɯɕɯŋgɯ<n><ind>/long time ago<cnjadv><ind>$ ^tɕe<cnj>//as for<pr>$^,<cm>/,<cm>$ ^nɤki<dem>/that<det><dem><sg>$^,<cm>/,<cm>$ ^lɯlu<n><ind>/cat<n><sg><ind>$ ^ci<det>/a<det><ind><sg>/one<num><sg>$ ^pjɤtu<cop><other>/be<vbser><other>$^,<cm>/,<cm>$ ^tɕendɤre<cnj>/then<cnjadv>$ ^βʑɯ<n><ind>/mouse<n><sg><ind>$ ^ci<det>/a<det><ind><sg>/one<num><sg>$ ^pjɤtu<cop><other>/be<vbser><other>$^.<sent>/.<sent>$
</pre>

Output of jya-eng:
<pre>
#long time ago , that, #cat a #be, then #mouse a #be
</pre>

====#2====
The original sentence:
<pre>
lɯlu nɯ kɯ nɤkinɯ, βʑɯ ri tundze ɕti
</pre>

The intended English translation: The cat ate the mouse,

Output of jya-eng-biltrans:
<pre>
^lɯlu<n><ind>/cat<n><sg><ind>$ ^nɯ<dem>/that<det><dem><sg>$ ^kɯ<post>/with<pr>$ ^nɤkinɯ<fill>/um<ij>$^,<cm>/,<cm>$ ^βʑɯ<n><ind>/mouse<n><sg><ind>$ ^ri<post>/at<pr>$ ^ndze<v><tv><ipfv>/eat<vblex><ipfv>$ ^ɕti<v><iv>/be<vbser>$^.<sent>/.<sent>$
</pre>

Output of jya-eng:
<pre>
#cat that with um, #mouse at #eat #be
</pre>

====#3====
The original sentence:

<pre>
βʑɯ chondɤre nɤki, kumpɣɤtɕɯ nɯ kɯ βzaŋsa tonɯpandʑi,
</pre>

The intended English translation: The mouse made friends with the sparrow,

Output of jya-eng-biltrans:
<pre>
^βʑɯ<n><ind>/mouse<n><sg><ind>$ ^chondɤre<com>/with<pr>$ ^nɤki<dem>/that<det><dem><sg>$^,<cm>/,<cm>$ ^kumpɣɤtɕɯ<n><ind>/sparrow<n><sg><ind>$ ^nɯ<dem>/that<det><dem><sg>$ ^kɯ<post>/with<pr>$ ^βzaŋsa<n><ind>/friend<n><sg><ind>$ ^tonɯpa<v><tv><du>/made<vblex><pp><du>$^,<cm>/,<cm>$^.<sent>/.<sent>$
</pre>

Output of jya-eng:
<pre>
#mouse with that, #sparrow that with #friend #made,
</pre>

====#4====
The original sentence:
<pre>
tɕe βzaŋsa tonɯpandʑi tɕe, wuma pjɤkɤmɯmindʑici
</pre>

The intended English translation: The two of them become friends and got along well

Output of jya-eng-biltrans:
<pre>
^tɕe<cnj>//as for<pr>$ ^βzaŋsa<n><ind>/friend<n><sg><ind>$ ^tonɯpa<v><tv><du>/made<vblex><pp><du>$ ^tɕe<cnj>//as for<pr>$^,<cm>/,<cm>$ ^wuma<adv>/very<adv>$ ^ɤmɯmi<v><iv><pii><du>/get along well<vblex><pii><du>$^.<sent>/.<sent>$</pre>
Output of jya-eng:
<pre>
#friend #made , very #get along well
</pre>

====#5====
The original sentence:
<pre>
maka cici ŋotɕu jɤarɯrindʑi ʑo tɯtɯrca ntsɯ juɕendʑi pjɤŋu
</pre>
The intended English translation: they always got together

Output of jya-eng-biltrans:
<pre>
^maka<adv>/at all<adv>$ ^cici<adv>/sometimes<adv>$ ^ŋotɕu<prn>/wherever<adv>$ ^*jɤarɯrindʑi/*jɤarɯrindʑi$ ^*ʑo/*ʑo$ ^*tɯtɯrca/*tɯtɯrca$ ^ntsɯ<adv>/always<adv>$ ^*juɕendʑi/*juɕendʑi$ ^ŋu<v><iv><pii>/be<vbser><pii>$^.<sent>/.<sent>$
</pre>
Output of jya-eng:
<pre>
at all sometimes wherever #each together always #go #be
</pre>

====#6====
The original sentence:
<pre>
kɤndza ci tu nɤ pjɯnɯkrondʑi
</pre>
The intended English translation: There was food to eat, they shared,

Output of jya-eng-biltrans:
<pre>
^kɤndza<n><ind>/food<n><sg><ind>$ ^ci<det>/a<det><ind><sg>/one<num><sg>$ ^tu<v><iv>/be<vbser>/exist<vblex>$ ^*nɤ/*nɤ$ ^*pjɯnɯkrondʑi/*pjɯnɯkrondʑi$^.<sent>/.<sent>$
</pre>
Output of jya-eng:
<pre>
#food a #be at #share
</pre>

====#7====
The original sentence:
<pre>
nɯ mɤʑɯ kɯmtɕhɯ kɯfse tɤtu nɤ, tɯɣrɤz ɲɯnɤɣrondʑi nɯ ra pjɤŋgrɤl
</pre>

The intended English translation: Also, when there was something to play with, they played together

Output of jya-eng-biltrans:
<pre>
^nɯ<dem>/that<det><dem><sg>$ ^mɤʑɯ<adv>/again<adv>$ ^kɯmtɕhɯ<n><ind>/toy<n><sg><ind>$ ^fse<v><tv><prc><sbj><ind>/resemble<vblex><prc><sbj><ind>$ ^tu<v><iv><aor>/be<vbser><aor>/exist<vblex><aor>$ ^nɤ<post>/at<pr>$^,<cm>/,<cm>$ ^tɯɣrɤz<adv>/together<adv>$ ^nɤɣro<v><tv><ipfv><du>/play<vblex><inf><ipfv><du>$ ^nɯ<dem>/that<det><dem><sg>$ ^ra<v><iv>/should<vbmod>$ ^ŋgrɤl<v><iv><pii>/usually like this<iv><pii>$^.<sent>/.<sent>$
</pre>

Output of jya-eng:
<pre>
that again #toy #resemble #be at, together #play that #should #usually like this
</pre>

====#8====
The original sentence:
<pre>
tɕhi kɤcha tukɤpjɤl kowa ntsɯ tuβzundʑi pjɤŋu tɕe
</pre>

The intended English translation: They were always trying to think of ways to evade that cat

Output of jya-eng-biltrans:
<pre>
^tɕhi<prn>/what<prn>$ ^cha<v><iv><prc><obj><ind>/able<adj><prc><obj><ind>/can<vbmod><prc><obj><ind>$ ^pjɤl<v><tv><inf><ipfv>/evade<vblex><inf><ipfv>$ ^kowa<n><ind>/method<n><sg><ind>$ ^ntsɯ<adv>/always<adv>$ ^βzu<v><tv><ipfv><du>/make<vblex><ipfv><du>$ ^ŋu<v><iv><pii>/be<vbser><pii>$ ^tɕe<cnj>//as for<pr>$^.<sent>/.<sent>$
</pre>

Output of jya-eng:
<pre>
#what #able #evade #method always #make #be
</pre>

====#9====
The original sentence:
<pre>
lɯlu nɯ kɯ βʑɯ ɯɕa tɕi pjɤrga, pɣɤtɕɯ ɯɕa tɕi pjɤrga ɕti tɕe.
</pre>

The intended English translation: The cat likes eating rat meat, and also likes sparrow meat.

Output of jya-eng-biltrans:
<pre>
^lɯlu<n><ind>/cat<n><sg><ind>$ ^nɯ<dem>/that<det><dem><sg>$ ^kɯ<post>/with<pr>$ ^βʑɯ<n><ind>/mouse<n><sg><ind>$ ^ɕa<n><px3sg>/meat<n><sg><px3sg>$ ^tɕi<adv>/also<adv>$ ^rga<v><iv><pii>/like<vblex><pii>$^,<cm>/,<cm>$ ^pɣɤtɕɯ<n><ind>/bird<n><sg><ind>$ ^ɕa<n><px3sg>/meat<n><sg><px3sg>$ ^tɕi<adv>/also<adv>$ ^rga<v><iv><pii>/like<vblex><pii>$ ^ɕti<v><iv>/be<vbser>$ ^tɕe<cnj>//as for<pr>$^.<sent>/.<sent>$^.<sent>/.<sent>$
</pre>

Output of jya-eng:
<pre>
#cat that with #mouse #meat also #like, #bird #meat also #like #be .
</pre>

====#10====
The original sentence:
<pre>
tɕe nɯ maʁ nɤ tɕe, βʑɯ nɯ kɯ wuma kɤrɤfsoʁ pjɤcha tɕe
</pre>

The intended English translation: since then, that mouse was very good at accumulating food

Output of jya-eng-biltrans:
<pre>
^tɕe<cnj>//as for<pr>$ ^nɯ maʁ nɤ<cnj>/or<cnjcoo>$ ^tɕe<cnj>//as for<pr>$^,<cm>/,<cm>$ ^βʑɯ<n><ind>/mouse<n><sg><ind>$ ^nɯ<dem>/that<det><dem><sg>$ ^kɯ<post>/with<pr>$ ^wuma<adv>/very<adv>$ ^rɤfsoʁ<v><iv><prc><obj><ind>/forage<vblex><prc><obj><ind>$ ^cha<v><iv><pii>/able<adj><pii>/can<vbmod><pii>$ ^tɕe<cnj>//as for<pr>$^.<sent>/.<sent>$
</pre>

Output of jya-eng:
<pre>
or , #mouse that with very #forage #able
</pre>

===Additions ===
These are some additions we made to our bilingual transducer beyond the labs.

* 5000+ lemmas to our Japhug transducer

* 5 new features covered in our Japhug morphological analyzer, including: imperfective prefixes, the peg circumfix, proximal/distal demonstratives, redesigned verb patterns to match the slot-based prefix system in Japhug, number suffixes on verbs.

* 2 new structural transfer rules: NP rule to combine nouns and possessed nouns; DP rule to place determiner before noun, and to take ergative case from postposition; vP rule to combine adverbs and verbs. These were made in the process of meeting our original goal, to match the SVO word order in English (Japhug is usually SOV or OSV)

(details listed for our own reference)

===Final evaluation===

Monolingual transducer stats:
*Updated precision and recall against the (updated) eval.test and eval.gold files:
<pre>
$ precisionRecall jya.eval.test.new.txt jya.eval.gold.txt
Totals: 79 forms, 179 tp, 212 fp, 0 tn, 153 fn
Precision: 45.78005%
Recall: 53.91566%</pre>
*Coverage over the large corpus:
<pre>
TOP UNKNOWN WORDS:
16 ^ɣɯ/*ɣɯ$
14 ^lɤβzaŋ/*lɤβzaŋ$
11 ^cho/*cho$
10 ^qartshɤs/*qartshɤs$
8 ^rɟɤlpu/*rɟɤlpu$
8 ^rcanɯ/*rcanɯ$
8 ^qhe/*qhe$
8 ^je/*je$
8 ^jamɤn/*jamɤn$
7 ^tɕɤn/*tɕɤn$
6 ^nɯmbala/*nɯmbala$
6 ^ndɤ/*ndɤ$
6 ^lɤari/*lɤari$
6 ^kɯki/*kɯki$
5 ^wo/*wo$
5 ^tɯɣjɤn/*tɯɣjɤn$
5 ^lɤɣe/*lɤɣe$
5 ^kɯsthɯci/*kɯsthɯci$
5 ^ciŋglɯɣ/*ciŋglɯɣ$
4 ^ɲɯsɯsɤm/*ɲɯsɯsɤm$
coverage: 4463 / 5019 (~0.88922096035066746364)
remaining unknown forms: 556
ambiguity: 9939 / 5019 (~1.98027495517035265989)
jya.corpus Mon May 8 02:13:49 PM EDT 2023 4463/5019 ~0.88922096035066746364 \| 9939/5019 ~1.98027495517035265989
</pre>
*The number of words in the large corpus: 3999
*The number of stems in the transducer): 6646

MT in jya-eng stats:
*WER and PER over longer corpus:

<pre>
Statistics about input files
-------------------------------------------------------
Number of words in reference: 3013
Number of words in test: 2444
Number of unknown words (marked with a star) in test: 1243
Percentage of unknown words: 50.86 %

Results when removing unknown-word marks (stars)
-------------------------------------------------------
Edit distance: 3138
Word error rate (WER): 104.15 %
Number of position-independent correct words: 57
Position-independent word error rate (PER): 98.11 %
</pre>
*The proportion of stems translated correctly in the longer corpus:
*Trimmed coverage over longer corpora: ~0.90917159763313609467
*Trimmed coverage over large corpora: ~0.88922096035066746364
*The number of tokens in longer corpora: 307
*The number of tokens in large corpora: 556

[[Category:Sp23_TranslationPairs ]] [[Category: Japhug]]

Japhug/Japhug and English

2023-05-08T22:41:09Z

Ylhamo1: /* Final evaluation */

==Resources for machine translation between [https://wikis.swarthmore.edu/ling073/Category:Japhug Japhug] and English==

===Developed resources===

[https://github.swarthmore.edu/Ling073-sp23/ling073-jya-eng-corpus Japhug-English corpus]

[https://wikis.swarthmore.edu/ling073/Japhug_and_English/Lexical_selection#jya_.E2.86.92_eng Lexical selection]

==External resources==
[https://github.swarthmore.edu/Ling073-sp23/ling073-jya-eng Apertium language pair for translating between Jiarong and English]

[https://github.swarthmore.edu/Ling073-sp23/ling073-jya Monolingual Japhug transducer]

==Jya → Eng evaluation ==

coverage (number of forms analysed) of Japhug transducer on jya.sentences.txt: 76.98 %

coverage of bilingual transducer (jya-eng.automorf.bin) on the same file: 28.61 %

===10 sentences:===

====#1====
The original sentence:
<pre>
kɯɕɯŋgɯ tɕe, nɤki, lɯlu ci pjɤtu, tɕendɤre βʑɯ ci pjɤtu
</pre>
The intended English translation: A long time ago, there was a cat and a mouse

Output of jya-eng-biltrans:
<pre>
^kɯɕɯŋgɯ<n><ind>/long time ago<cnjadv><ind>$ ^tɕe<cnj>//as for<pr>$^,<cm>/,<cm>$ ^nɤki<dem>/that<det><dem><sg>$^,<cm>/,<cm>$ ^lɯlu<n><ind>/cat<n><sg><ind>$ ^ci<det>/a<det><ind><sg>/one<num><sg>$ ^pjɤtu<cop><other>/be<vbser><other>$^,<cm>/,<cm>$ ^tɕendɤre<cnj>/then<cnjadv>$ ^βʑɯ<n><ind>/mouse<n><sg><ind>$ ^ci<det>/a<det><ind><sg>/one<num><sg>$ ^pjɤtu<cop><other>/be<vbser><other>$^.<sent>/.<sent>$
</pre>

Output of jya-eng:
<pre>
#long time ago , that, #cat a #be, then #mouse a #be
</pre>

====#2====
The original sentence:
<pre>
lɯlu nɯ kɯ nɤkinɯ, βʑɯ ri tundze ɕti
</pre>

The intended English translation: The cat ate the mouse,

Output of jya-eng-biltrans:
<pre>
^lɯlu<n><ind>/cat<n><sg><ind>$ ^nɯ<dem>/that<det><dem><sg>$ ^kɯ<post>/with<pr>$ ^nɤkinɯ<fill>/um<ij>$^,<cm>/,<cm>$ ^βʑɯ<n><ind>/mouse<n><sg><ind>$ ^ri<post>/at<pr>$ ^ndze<v><tv><ipfv>/eat<vblex><ipfv>$ ^ɕti<v><iv>/be<vbser>$^.<sent>/.<sent>$
</pre>

Output of jya-eng:
<pre>
#cat that with um, #mouse at #eat #be
</pre>

====#3====
The original sentence:

<pre>
βʑɯ chondɤre nɤki, kumpɣɤtɕɯ nɯ kɯ βzaŋsa tonɯpandʑi,
</pre>

The intended English translation: The mouse made friends with the sparrow,

Output of jya-eng-biltrans:
<pre>
^βʑɯ<n><ind>/mouse<n><sg><ind>$ ^chondɤre<com>/with<pr>$ ^nɤki<dem>/that<det><dem><sg>$^,<cm>/,<cm>$ ^kumpɣɤtɕɯ<n><ind>/sparrow<n><sg><ind>$ ^nɯ<dem>/that<det><dem><sg>$ ^kɯ<post>/with<pr>$ ^βzaŋsa<n><ind>/friend<n><sg><ind>$ ^tonɯpa<v><tv><du>/made<vblex><pp><du>$^,<cm>/,<cm>$^.<sent>/.<sent>$
</pre>

Output of jya-eng:
<pre>
#mouse with that, #sparrow that with #friend #made,
</pre>

====#4====
The original sentence:
<pre>
tɕe βzaŋsa tonɯpandʑi tɕe, wuma pjɤkɤmɯmindʑici
</pre>

The intended English translation: The two of them become friends and got along well

Output of jya-eng-biltrans:
<pre>
^tɕe<cnj>//as for<pr>$ ^βzaŋsa<n><ind>/friend<n><sg><ind>$ ^tonɯpa<v><tv><du>/made<vblex><pp><du>$ ^tɕe<cnj>//as for<pr>$^,<cm>/,<cm>$ ^wuma<adv>/very<adv>$ ^ɤmɯmi<v><iv><pii><du>/get along well<vblex><pii><du>$^.<sent>/.<sent>$</pre>
Output of jya-eng:
<pre>
#friend #made , very #get along well
</pre>

====#5====
The original sentence:
<pre>
maka cici ŋotɕu jɤarɯrindʑi ʑo tɯtɯrca ntsɯ juɕendʑi pjɤŋu
</pre>
The intended English translation: they always got together

Output of jya-eng-biltrans:
<pre>
^maka<adv>/at all<adv>$ ^cici<adv>/sometimes<adv>$ ^ŋotɕu<prn>/wherever<adv>$ ^*jɤarɯrindʑi/*jɤarɯrindʑi$ ^*ʑo/*ʑo$ ^*tɯtɯrca/*tɯtɯrca$ ^ntsɯ<adv>/always<adv>$ ^*juɕendʑi/*juɕendʑi$ ^ŋu<v><iv><pii>/be<vbser><pii>$^.<sent>/.<sent>$
</pre>
Output of jya-eng:
<pre>
at all sometimes wherever #each together always #go #be
</pre>

====#6====
The original sentence:
<pre>
kɤndza ci tu nɤ pjɯnɯkrondʑi
</pre>
The intended English translation: There was food to eat, they shared,

Output of jya-eng-biltrans:
<pre>
^kɤndza<n><ind>/food<n><sg><ind>$ ^ci<det>/a<det><ind><sg>/one<num><sg>$ ^tu<v><iv>/be<vbser>/exist<vblex>$ ^*nɤ/*nɤ$ ^*pjɯnɯkrondʑi/*pjɯnɯkrondʑi$^.<sent>/.<sent>$
</pre>
Output of jya-eng:
<pre>
#food a #be at #share
</pre>

====#7====
The original sentence:
<pre>
nɯ mɤʑɯ kɯmtɕhɯ kɯfse tɤtu nɤ, tɯɣrɤz ɲɯnɤɣrondʑi nɯ ra pjɤŋgrɤl
</pre>

The intended English translation: Also, when there was something to play with, they played together

Output of jya-eng-biltrans:
<pre>
^nɯ<dem>/that<det><dem><sg>$ ^mɤʑɯ<adv>/again<adv>$ ^kɯmtɕhɯ<n><ind>/toy<n><sg><ind>$ ^fse<v><tv><prc><sbj><ind>/resemble<vblex><prc><sbj><ind>$ ^tu<v><iv><aor>/be<vbser><aor>/exist<vblex><aor>$ ^nɤ<post>/at<pr>$^,<cm>/,<cm>$ ^tɯɣrɤz<adv>/together<adv>$ ^nɤɣro<v><tv><ipfv><du>/play<vblex><inf><ipfv><du>$ ^nɯ<dem>/that<det><dem><sg>$ ^ra<v><iv>/should<vbmod>$ ^ŋgrɤl<v><iv><pii>/usually like this<iv><pii>$^.<sent>/.<sent>$
</pre>

Output of jya-eng:
<pre>
that again #toy #resemble #be at, together #play that #should #usually like this
</pre>

====#8====
The original sentence:
<pre>
tɕhi kɤcha tukɤpjɤl kowa ntsɯ tuβzundʑi pjɤŋu tɕe
</pre>

The intended English translation: They were always trying to think of ways to evade that cat

Output of jya-eng-biltrans:
<pre>
^tɕhi<prn>/what<prn>$ ^cha<v><iv><prc><obj><ind>/able<adj><prc><obj><ind>/can<vbmod><prc><obj><ind>$ ^pjɤl<v><tv><inf><ipfv>/evade<vblex><inf><ipfv>$ ^kowa<n><ind>/method<n><sg><ind>$ ^ntsɯ<adv>/always<adv>$ ^βzu<v><tv><ipfv><du>/make<vblex><ipfv><du>$ ^ŋu<v><iv><pii>/be<vbser><pii>$ ^tɕe<cnj>//as for<pr>$^.<sent>/.<sent>$
</pre>

Output of jya-eng:
<pre>
#what #able #evade #method always #make #be
</pre>

====#9====
The original sentence:
<pre>
lɯlu nɯ kɯ βʑɯ ɯɕa tɕi pjɤrga, pɣɤtɕɯ ɯɕa tɕi pjɤrga ɕti tɕe.
</pre>

The intended English translation: The cat likes eating rat meat, and also likes sparrow meat.

Output of jya-eng-biltrans:
<pre>
^lɯlu<n><ind>/cat<n><sg><ind>$ ^nɯ<dem>/that<det><dem><sg>$ ^kɯ<post>/with<pr>$ ^βʑɯ<n><ind>/mouse<n><sg><ind>$ ^ɕa<n><px3sg>/meat<n><sg><px3sg>$ ^tɕi<adv>/also<adv>$ ^rga<v><iv><pii>/like<vblex><pii>$^,<cm>/,<cm>$ ^pɣɤtɕɯ<n><ind>/bird<n><sg><ind>$ ^ɕa<n><px3sg>/meat<n><sg><px3sg>$ ^tɕi<adv>/also<adv>$ ^rga<v><iv><pii>/like<vblex><pii>$ ^ɕti<v><iv>/be<vbser>$ ^tɕe<cnj>//as for<pr>$^.<sent>/.<sent>$^.<sent>/.<sent>$
</pre>

Output of jya-eng:
<pre>
#cat that with #mouse #meat also #like, #bird #meat also #like #be .
</pre>

====#10====
The original sentence:
<pre>
tɕe nɯ maʁ nɤ tɕe, βʑɯ nɯ kɯ wuma kɤrɤfsoʁ pjɤcha tɕe
</pre>

The intended English translation: since then, that mouse was very good at accumulating food

Output of jya-eng-biltrans:
<pre>
^tɕe<cnj>//as for<pr>$ ^nɯ maʁ nɤ<cnj>/or<cnjcoo>$ ^tɕe<cnj>//as for<pr>$^,<cm>/,<cm>$ ^βʑɯ<n><ind>/mouse<n><sg><ind>$ ^nɯ<dem>/that<det><dem><sg>$ ^kɯ<post>/with<pr>$ ^wuma<adv>/very<adv>$ ^rɤfsoʁ<v><iv><prc><obj><ind>/forage<vblex><prc><obj><ind>$ ^cha<v><iv><pii>/able<adj><pii>/can<vbmod><pii>$ ^tɕe<cnj>//as for<pr>$^.<sent>/.<sent>$
</pre>

Output of jya-eng:
<pre>
or , #mouse that with very #forage #able
</pre>

===Additions ===
These are some additions we made to our bilingual transducer beyond the labs.

* 5000+ lemmas to our Japhug transducer

* 5 new features covered in our Japhug morphological analyzer, including: imperfective prefixes, the peg circumfix, proximal/distal demonstratives, redesigned verb patterns to match the slot-based prefix system in Japhug, number suffixes on verbs.

* 2 new structural transfer rules: NP rule to combine nouns and possessed nouns; DP rule to place determiner before noun, and to take ergative case from postposition; vP rule to combine adverbs and verbs. These were made in the process of meeting our original goal, to match the SVO word order in English (Japhug is usually SOV or OSV)

(details listed for our own reference)

===Final evaluation===

Monolingual transducer stats:
*Updated precision and recall against the (updated) eval.test and eval.gold files:
<pre>
$ precisionRecall jya.eval.test.new.txt jya.eval.gold.txt
Totals: 79 forms, 179 tp, 212 fp, 0 tn, 153 fn
Precision: 45.78005%
Recall: 53.91566%</pre>
*Coverage over the large corpus:
<pre>
TOP UNKNOWN WORDS:
16 ^ɣɯ/*ɣɯ$
14 ^lɤβzaŋ/*lɤβzaŋ$
11 ^cho/*cho$
10 ^qartshɤs/*qartshɤs$
8 ^rɟɤlpu/*rɟɤlpu$
8 ^rcanɯ/*rcanɯ$
8 ^qhe/*qhe$
8 ^je/*je$
8 ^jamɤn/*jamɤn$
7 ^tɕɤn/*tɕɤn$
6 ^nɯmbala/*nɯmbala$
6 ^ndɤ/*ndɤ$
6 ^lɤari/*lɤari$
6 ^kɯki/*kɯki$
5 ^wo/*wo$
5 ^tɯɣjɤn/*tɯɣjɤn$
5 ^lɤɣe/*lɤɣe$
5 ^kɯsthɯci/*kɯsthɯci$
5 ^ciŋglɯɣ/*ciŋglɯɣ$
4 ^ɲɯsɯsɤm/*ɲɯsɯsɤm$
coverage: 4463 / 5019 (~0.88922096035066746364)
remaining unknown forms: 556
ambiguity: 9939 / 5019 (~1.98027495517035265989)
jya.corpus Mon May 8 02:13:49 PM EDT 2023 4463/5019 ~0.88922096035066746364 \| 9939/5019 ~1.98027495517035265989
</pre>
*The number of words in the large corpus: 3999
*The number of stems in the transducer): 6646

MT in jya-eng stats:
*WER and PER over longer corpus:

<pre>
Statistics about input files
-------------------------------------------------------
Number of words in reference: 3013
Number of words in test: 2444
Number of unknown words (marked with a star) in test: 1243
Percentage of unknown words: 50.86 %

Results when removing unknown-word marks (stars)
-------------------------------------------------------
Edit distance: 3138
Word error rate (WER): 104.15 %
Number of position-independent correct words: 57
Position-independent word error rate (PER): 98.11 %
</pre>
*The proportion of stems translated correctly in the longer corpus:
*Trimmed coverage over longer and large corpora:
*The number of tokens in longer and large corpora:

[[Category:Sp23_TranslationPairs ]] [[Category: Japhug]]

Japhug/Japhug and English

2023-05-08T22:13:25Z

Ylhamo1: /* Final evaluation */

==Resources for machine translation between [https://wikis.swarthmore.edu/ling073/Category:Japhug Japhug] and English==

===Developed resources===

[https://github.swarthmore.edu/Ling073-sp23/ling073-jya-eng-corpus Japhug-English corpus]

[https://wikis.swarthmore.edu/ling073/Japhug_and_English/Lexical_selection#jya_.E2.86.92_eng Lexical selection]

==External resources==
[https://github.swarthmore.edu/Ling073-sp23/ling073-jya-eng Apertium language pair for translating between Jiarong and English]

[https://github.swarthmore.edu/Ling073-sp23/ling073-jya Monolingual Japhug transducer]

==Jya → Eng evaluation ==

coverage (number of forms analysed) of Japhug transducer on jya.sentences.txt: 76.98 %

coverage of bilingual transducer (jya-eng.automorf.bin) on the same file: 28.61 %

===10 sentences:===

====#1====
The original sentence:
<pre>
kɯɕɯŋgɯ tɕe, nɤki, lɯlu ci pjɤtu, tɕendɤre βʑɯ ci pjɤtu
</pre>
The intended English translation: A long time ago, there was a cat and a mouse

Output of jya-eng-biltrans:
<pre>
^kɯɕɯŋgɯ<n><ind>/long time ago<cnjadv><ind>$ ^tɕe<cnj>//as for<pr>$^,<cm>/,<cm>$ ^nɤki<dem>/that<det><dem><sg>$^,<cm>/,<cm>$ ^lɯlu<n><ind>/cat<n><sg><ind>$ ^ci<det>/a<det><ind><sg>/one<num><sg>$ ^pjɤtu<cop><other>/be<vbser><other>$^,<cm>/,<cm>$ ^tɕendɤre<cnj>/then<cnjadv>$ ^βʑɯ<n><ind>/mouse<n><sg><ind>$ ^ci<det>/a<det><ind><sg>/one<num><sg>$ ^pjɤtu<cop><other>/be<vbser><other>$^.<sent>/.<sent>$
</pre>

Output of jya-eng:
<pre>
#long time ago , that, #cat a #be, then #mouse a #be
</pre>

====#2====
The original sentence:
<pre>
lɯlu nɯ kɯ nɤkinɯ, βʑɯ ri tundze ɕti
</pre>

The intended English translation: The cat ate the mouse,

Output of jya-eng-biltrans:
<pre>
^lɯlu<n><ind>/cat<n><sg><ind>$ ^nɯ<dem>/that<det><dem><sg>$ ^kɯ<post>/with<pr>$ ^nɤkinɯ<fill>/um<ij>$^,<cm>/,<cm>$ ^βʑɯ<n><ind>/mouse<n><sg><ind>$ ^ri<post>/at<pr>$ ^ndze<v><tv><ipfv>/eat<vblex><ipfv>$ ^ɕti<v><iv>/be<vbser>$^.<sent>/.<sent>$
</pre>

Output of jya-eng:
<pre>
#cat that with um, #mouse at #eat #be
</pre>

====#3====
The original sentence:

<pre>
βʑɯ chondɤre nɤki, kumpɣɤtɕɯ nɯ kɯ βzaŋsa tonɯpandʑi,
</pre>

The intended English translation: The mouse made friends with the sparrow,

Output of jya-eng-biltrans:
<pre>
^βʑɯ<n><ind>/mouse<n><sg><ind>$ ^chondɤre<com>/with<pr>$ ^nɤki<dem>/that<det><dem><sg>$^,<cm>/,<cm>$ ^kumpɣɤtɕɯ<n><ind>/sparrow<n><sg><ind>$ ^nɯ<dem>/that<det><dem><sg>$ ^kɯ<post>/with<pr>$ ^βzaŋsa<n><ind>/friend<n><sg><ind>$ ^tonɯpa<v><tv><du>/made<vblex><pp><du>$^,<cm>/,<cm>$^.<sent>/.<sent>$
</pre>

Output of jya-eng:
<pre>
#mouse with that, #sparrow that with #friend #made,
</pre>

====#4====
The original sentence:
<pre>
tɕe βzaŋsa tonɯpandʑi tɕe, wuma pjɤkɤmɯmindʑici
</pre>

The intended English translation: The two of them become friends and got along well

Output of jya-eng-biltrans:
<pre>
^tɕe<cnj>//as for<pr>$ ^βzaŋsa<n><ind>/friend<n><sg><ind>$ ^tonɯpa<v><tv><du>/made<vblex><pp><du>$ ^tɕe<cnj>//as for<pr>$^,<cm>/,<cm>$ ^wuma<adv>/very<adv>$ ^ɤmɯmi<v><iv><pii><du>/get along well<vblex><pii><du>$^.<sent>/.<sent>$</pre>
Output of jya-eng:
<pre>
#friend #made , very #get along well
</pre>

====#5====
The original sentence:
<pre>
maka cici ŋotɕu jɤarɯrindʑi ʑo tɯtɯrca ntsɯ juɕendʑi pjɤŋu
</pre>
The intended English translation: they always got together

Output of jya-eng-biltrans:
<pre>
^maka<adv>/at all<adv>$ ^cici<adv>/sometimes<adv>$ ^ŋotɕu<prn>/wherever<adv>$ ^*jɤarɯrindʑi/*jɤarɯrindʑi$ ^*ʑo/*ʑo$ ^*tɯtɯrca/*tɯtɯrca$ ^ntsɯ<adv>/always<adv>$ ^*juɕendʑi/*juɕendʑi$ ^ŋu<v><iv><pii>/be<vbser><pii>$^.<sent>/.<sent>$
</pre>
Output of jya-eng:
<pre>
at all sometimes wherever #each together always #go #be
</pre>

====#6====
The original sentence:
<pre>
kɤndza ci tu nɤ pjɯnɯkrondʑi
</pre>
The intended English translation: There was food to eat, they shared,

Output of jya-eng-biltrans:
<pre>
^kɤndza<n><ind>/food<n><sg><ind>$ ^ci<det>/a<det><ind><sg>/one<num><sg>$ ^tu<v><iv>/be<vbser>/exist<vblex>$ ^*nɤ/*nɤ$ ^*pjɯnɯkrondʑi/*pjɯnɯkrondʑi$^.<sent>/.<sent>$
</pre>
Output of jya-eng:
<pre>
#food a #be at #share
</pre>

====#7====
The original sentence:
<pre>
nɯ mɤʑɯ kɯmtɕhɯ kɯfse tɤtu nɤ, tɯɣrɤz ɲɯnɤɣrondʑi nɯ ra pjɤŋgrɤl
</pre>

The intended English translation: Also, when there was something to play with, they played together

Output of jya-eng-biltrans:
<pre>
^nɯ<dem>/that<det><dem><sg>$ ^mɤʑɯ<adv>/again<adv>$ ^kɯmtɕhɯ<n><ind>/toy<n><sg><ind>$ ^fse<v><tv><prc><sbj><ind>/resemble<vblex><prc><sbj><ind>$ ^tu<v><iv><aor>/be<vbser><aor>/exist<vblex><aor>$ ^nɤ<post>/at<pr>$^,<cm>/,<cm>$ ^tɯɣrɤz<adv>/together<adv>$ ^nɤɣro<v><tv><ipfv><du>/play<vblex><inf><ipfv><du>$ ^nɯ<dem>/that<det><dem><sg>$ ^ra<v><iv>/should<vbmod>$ ^ŋgrɤl<v><iv><pii>/usually like this<iv><pii>$^.<sent>/.<sent>$
</pre>

Output of jya-eng:
<pre>
that again #toy #resemble #be at, together #play that #should #usually like this
</pre>

====#8====
The original sentence:
<pre>
tɕhi kɤcha tukɤpjɤl kowa ntsɯ tuβzundʑi pjɤŋu tɕe
</pre>

The intended English translation: They were always trying to think of ways to evade that cat

Output of jya-eng-biltrans:
<pre>
^tɕhi<prn>/what<prn>$ ^cha<v><iv><prc><obj><ind>/able<adj><prc><obj><ind>/can<vbmod><prc><obj><ind>$ ^pjɤl<v><tv><inf><ipfv>/evade<vblex><inf><ipfv>$ ^kowa<n><ind>/method<n><sg><ind>$ ^ntsɯ<adv>/always<adv>$ ^βzu<v><tv><ipfv><du>/make<vblex><ipfv><du>$ ^ŋu<v><iv><pii>/be<vbser><pii>$ ^tɕe<cnj>//as for<pr>$^.<sent>/.<sent>$
</pre>

Output of jya-eng:
<pre>
#what #able #evade #method always #make #be
</pre>

====#9====
The original sentence:
<pre>
lɯlu nɯ kɯ βʑɯ ɯɕa tɕi pjɤrga, pɣɤtɕɯ ɯɕa tɕi pjɤrga ɕti tɕe.
</pre>

The intended English translation: The cat likes eating rat meat, and also likes sparrow meat.

Output of jya-eng-biltrans:
<pre>
^lɯlu<n><ind>/cat<n><sg><ind>$ ^nɯ<dem>/that<det><dem><sg>$ ^kɯ<post>/with<pr>$ ^βʑɯ<n><ind>/mouse<n><sg><ind>$ ^ɕa<n><px3sg>/meat<n><sg><px3sg>$ ^tɕi<adv>/also<adv>$ ^rga<v><iv><pii>/like<vblex><pii>$^,<cm>/,<cm>$ ^pɣɤtɕɯ<n><ind>/bird<n><sg><ind>$ ^ɕa<n><px3sg>/meat<n><sg><px3sg>$ ^tɕi<adv>/also<adv>$ ^rga<v><iv><pii>/like<vblex><pii>$ ^ɕti<v><iv>/be<vbser>$ ^tɕe<cnj>//as for<pr>$^.<sent>/.<sent>$^.<sent>/.<sent>$
</pre>

Output of jya-eng:
<pre>
#cat that with #mouse #meat also #like, #bird #meat also #like #be .
</pre>

====#10====
The original sentence:
<pre>
tɕe nɯ maʁ nɤ tɕe, βʑɯ nɯ kɯ wuma kɤrɤfsoʁ pjɤcha tɕe
</pre>

The intended English translation: since then, that mouse was very good at accumulating food

Output of jya-eng-biltrans:
<pre>
^tɕe<cnj>//as for<pr>$ ^nɯ maʁ nɤ<cnj>/or<cnjcoo>$ ^tɕe<cnj>//as for<pr>$^,<cm>/,<cm>$ ^βʑɯ<n><ind>/mouse<n><sg><ind>$ ^nɯ<dem>/that<det><dem><sg>$ ^kɯ<post>/with<pr>$ ^wuma<adv>/very<adv>$ ^rɤfsoʁ<v><iv><prc><obj><ind>/forage<vblex><prc><obj><ind>$ ^cha<v><iv><pii>/able<adj><pii>/can<vbmod><pii>$ ^tɕe<cnj>//as for<pr>$^.<sent>/.<sent>$
</pre>

Output of jya-eng:
<pre>
or , #mouse that with very #forage #able
</pre>

===Additions ===
These are some additions we made to our bilingual transducer beyond the labs.

* 5000+ lemmas to our Japhug transducer

* 5 new features covered in our Japhug morphological analyzer, including: imperfective prefixes, the peg circumfix, proximal/distal demonstratives, redesigned verb patterns to match the slot-based prefix system in Japhug, number suffixes on verbs.

* 2 new structural transfer rules: NP rule to combine nouns and possessed nouns; DP rule to place determiner before noun, and to take ergative case from postposition; vP rule to combine adverbs and verbs. These were made in the process of meeting our original goal, to match the SVO word order in English (Japhug is usually SOV or OSV)

(details listed for our own reference)

===Final evaluation===

Monolingual transducer stats:
*Updated precision and recall against the (updated) eval.test and eval.gold files:
<pre>
ERROR: different number of annotated (5019) and test (5059) cohorts; check these: pjɯ́wɣzɣɤtɕa, ，, #, \, \{, \}, @, &, gt;dongdong&lt, gt;you&lt, ɲɯŋul, .., nɯ maʁ nɤ, ..., pjɯ́wɣzɣɤtɕa，, , ɲɯŋu，, gt, lt, you
</pre>
*Coverage over the large corpus:
<pre>
TOP UNKNOWN WORDS:
16 ^ɣɯ/*ɣɯ$
14 ^lɤβzaŋ/*lɤβzaŋ$
11 ^cho/*cho$
10 ^qartshɤs/*qartshɤs$
8 ^rɟɤlpu/*rɟɤlpu$
8 ^rcanɯ/*rcanɯ$
8 ^qhe/*qhe$
8 ^je/*je$
8 ^jamɤn/*jamɤn$
7 ^tɕɤn/*tɕɤn$
6 ^nɯmbala/*nɯmbala$
6 ^ndɤ/*ndɤ$
6 ^lɤari/*lɤari$
6 ^kɯki/*kɯki$
5 ^wo/*wo$
5 ^tɯɣjɤn/*tɯɣjɤn$
5 ^lɤɣe/*lɤɣe$
5 ^kɯsthɯci/*kɯsthɯci$
5 ^ciŋglɯɣ/*ciŋglɯɣ$
4 ^ɲɯsɯsɤm/*ɲɯsɯsɤm$
coverage: 4463 / 5019 (~0.88922096035066746364)
remaining unknown forms: 556
ambiguity: 9939 / 5019 (~1.98027495517035265989)
jya.corpus Mon May 8 02:13:49 PM EDT 2023 4463/5019 ~0.88922096035066746364 \| 9939/5019 ~1.98027495517035265989
</pre>
*The number of words in the large corpus: 3999
*The number of stems in the transducer): 6646

MT in jya-eng stats:
*WER and PER over longer corpus:

<pre>
Statistics about input files
-------------------------------------------------------
Number of words in reference: 3013
Number of words in test: 2444
Number of unknown words (marked with a star) in test: 1243
Percentage of unknown words: 50.86 %

Results when removing unknown-word marks (stars)
-------------------------------------------------------
Edit distance: 3138
Word error rate (WER): 104.15 %
Number of position-independent correct words: 57
Position-independent word error rate (PER): 98.11 %
</pre>
*The proportion of stems translated correctly in the longer corpus:
*Trimmed coverage over longer and large corpora:
*The number of tokens in longer and large corpora:

[[Category:Sp23_TranslationPairs ]] [[Category: Japhug]]

Japhug/Japhug and English

2023-05-08T18:44:36Z

Ylhamo1: /* Final evaluation */

==Resources for machine translation between [https://wikis.swarthmore.edu/ling073/Category:Japhug Japhug] and English==

===Developed resources===

[https://github.swarthmore.edu/Ling073-sp23/ling073-jya-eng-corpus Japhug-English corpus]

[https://wikis.swarthmore.edu/ling073/Japhug_and_English/Lexical_selection#jya_.E2.86.92_eng Lexical selection]

==External resources==
[https://github.swarthmore.edu/Ling073-sp23/ling073-jya-eng Apertium language pair for translating between Jiarong and English]

[https://github.swarthmore.edu/Ling073-sp23/ling073-jya Monolingual Japhug transducer]

==Jya → Eng evaluation ==

coverage (number of forms analysed) of Japhug transducer on jya.sentences.txt: 76.98 %

coverage of bilingual transducer (jya-eng.automorf.bin) on the same file: 28.61 %

===10 sentences:===

====#1====
The original sentence:
<pre>
kɯɕɯŋgɯ tɕe, nɤki, lɯlu ci pjɤtu, tɕendɤre βʑɯ ci pjɤtu
</pre>
The intended English translation: A long time ago, there was a cat and a mouse

Output of jya-eng-biltrans:
<pre>
^kɯɕɯŋgɯ<n><ind>/long time ago<cnjadv><ind>$ ^tɕe<cnj>//as for<pr>$^,<cm>/,<cm>$ ^nɤki<dem>/that<det><dem><sg>$^,<cm>/,<cm>$ ^lɯlu<n><ind>/cat<n><sg><ind>$ ^ci<det>/a<det><ind><sg>/one<num><sg>$ ^pjɤtu<cop><other>/be<vbser><other>$^,<cm>/,<cm>$ ^tɕendɤre<cnj>/then<cnjadv>$ ^βʑɯ<n><ind>/mouse<n><sg><ind>$ ^ci<det>/a<det><ind><sg>/one<num><sg>$ ^pjɤtu<cop><other>/be<vbser><other>$^.<sent>/.<sent>$
</pre>

Output of jya-eng:
<pre>
#long time ago , that, #cat a #be, then #mouse a #be
</pre>

====#2====
The original sentence:
<pre>
lɯlu nɯ kɯ nɤkinɯ, βʑɯ ri tundze ɕti
</pre>

The intended English translation: The cat ate the mouse,

Output of jya-eng-biltrans:
<pre>
^lɯlu<n><ind>/cat<n><sg><ind>$ ^nɯ<dem>/that<det><dem><sg>$ ^kɯ<post>/with<pr>$ ^nɤkinɯ<fill>/um<ij>$^,<cm>/,<cm>$ ^βʑɯ<n><ind>/mouse<n><sg><ind>$ ^ri<post>/at<pr>$ ^ndze<v><tv><ipfv>/eat<vblex><ipfv>$ ^ɕti<v><iv>/be<vbser>$^.<sent>/.<sent>$
</pre>

Output of jya-eng:
<pre>
#cat that with um, #mouse at #eat #be
</pre>

====#3====
The original sentence:

<pre>
βʑɯ chondɤre nɤki, kumpɣɤtɕɯ nɯ kɯ βzaŋsa tonɯpandʑi,
</pre>

The intended English translation: The mouse made friends with the sparrow,

Output of jya-eng-biltrans:
<pre>
^βʑɯ<n><ind>/mouse<n><sg><ind>$ ^chondɤre<com>/with<pr>$ ^nɤki<dem>/that<det><dem><sg>$^,<cm>/,<cm>$ ^kumpɣɤtɕɯ<n><ind>/sparrow<n><sg><ind>$ ^nɯ<dem>/that<det><dem><sg>$ ^kɯ<post>/with<pr>$ ^βzaŋsa<n><ind>/friend<n><sg><ind>$ ^tonɯpa<v><tv><du>/made<vblex><pp><du>$^,<cm>/,<cm>$^.<sent>/.<sent>$
</pre>

Output of jya-eng:
<pre>
#mouse with that, #sparrow that with #friend #made,
</pre>

====#4====
The original sentence:
<pre>
tɕe βzaŋsa tonɯpandʑi tɕe, wuma pjɤkɤmɯmindʑici
</pre>

The intended English translation: The two of them become friends and got along well

Output of jya-eng-biltrans:
<pre>
^tɕe<cnj>//as for<pr>$ ^βzaŋsa<n><ind>/friend<n><sg><ind>$ ^tonɯpa<v><tv><du>/made<vblex><pp><du>$ ^tɕe<cnj>//as for<pr>$^,<cm>/,<cm>$ ^wuma<adv>/very<adv>$ ^ɤmɯmi<v><iv><pii><du>/get along well<vblex><pii><du>$^.<sent>/.<sent>$</pre>
Output of jya-eng:
<pre>
#friend #made , very #get along well
</pre>

====#5====
The original sentence:
<pre>
maka cici ŋotɕu jɤarɯrindʑi ʑo tɯtɯrca ntsɯ juɕendʑi pjɤŋu
</pre>
The intended English translation: they always got together

Output of jya-eng-biltrans:
<pre>
^maka<adv>/at all<adv>$ ^cici<adv>/sometimes<adv>$ ^ŋotɕu<prn>/wherever<adv>$ ^*jɤarɯrindʑi/*jɤarɯrindʑi$ ^*ʑo/*ʑo$ ^*tɯtɯrca/*tɯtɯrca$ ^ntsɯ<adv>/always<adv>$ ^*juɕendʑi/*juɕendʑi$ ^ŋu<v><iv><pii>/be<vbser><pii>$^.<sent>/.<sent>$
</pre>
Output of jya-eng:
<pre>
at all sometimes wherever #each together always #go #be
</pre>

====#6====
The original sentence:
<pre>
kɤndza ci tu nɤ pjɯnɯkrondʑi
</pre>
The intended English translation: There was food to eat, they shared,

Output of jya-eng-biltrans:
<pre>
^kɤndza<n><ind>/food<n><sg><ind>$ ^ci<det>/a<det><ind><sg>/one<num><sg>$ ^tu<v><iv>/be<vbser>/exist<vblex>$ ^*nɤ/*nɤ$ ^*pjɯnɯkrondʑi/*pjɯnɯkrondʑi$^.<sent>/.<sent>$
</pre>
Output of jya-eng:
<pre>
#food a #be at #share
</pre>

====#7====
The original sentence:
<pre>
nɯ mɤʑɯ kɯmtɕhɯ kɯfse tɤtu nɤ, tɯɣrɤz ɲɯnɤɣrondʑi nɯ ra pjɤŋgrɤl
</pre>

The intended English translation: Also, when there was something to play with, they played together

Output of jya-eng-biltrans:
<pre>
^nɯ<dem>/that<det><dem><sg>$ ^mɤʑɯ<adv>/again<adv>$ ^kɯmtɕhɯ<n><ind>/toy<n><sg><ind>$ ^fse<v><tv><prc><sbj><ind>/resemble<vblex><prc><sbj><ind>$ ^tu<v><iv><aor>/be<vbser><aor>/exist<vblex><aor>$ ^nɤ<post>/at<pr>$^,<cm>/,<cm>$ ^tɯɣrɤz<adv>/together<adv>$ ^nɤɣro<v><tv><ipfv><du>/play<vblex><inf><ipfv><du>$ ^nɯ<dem>/that<det><dem><sg>$ ^ra<v><iv>/should<vbmod>$ ^ŋgrɤl<v><iv><pii>/usually like this<iv><pii>$^.<sent>/.<sent>$
</pre>

Output of jya-eng:
<pre>
that again #toy #resemble #be at, together #play that #should #usually like this
</pre>

====#8====
The original sentence:
<pre>
tɕhi kɤcha tukɤpjɤl kowa ntsɯ tuβzundʑi pjɤŋu tɕe
</pre>

The intended English translation: They were always trying to think of ways to evade that cat

Output of jya-eng-biltrans:
<pre>
^tɕhi<prn>/what<prn>$ ^cha<v><iv><prc><obj><ind>/able<adj><prc><obj><ind>/can<vbmod><prc><obj><ind>$ ^pjɤl<v><tv><inf><ipfv>/evade<vblex><inf><ipfv>$ ^kowa<n><ind>/method<n><sg><ind>$ ^ntsɯ<adv>/always<adv>$ ^βzu<v><tv><ipfv><du>/make<vblex><ipfv><du>$ ^ŋu<v><iv><pii>/be<vbser><pii>$ ^tɕe<cnj>//as for<pr>$^.<sent>/.<sent>$
</pre>

Output of jya-eng:
<pre>
#what #able #evade #method always #make #be
</pre>

====#9====
The original sentence:
<pre>
lɯlu nɯ kɯ βʑɯ ɯɕa tɕi pjɤrga, pɣɤtɕɯ ɯɕa tɕi pjɤrga ɕti tɕe.
</pre>

The intended English translation: The cat likes eating rat meat, and also likes sparrow meat.

Output of jya-eng-biltrans:
<pre>
^lɯlu<n><ind>/cat<n><sg><ind>$ ^nɯ<dem>/that<det><dem><sg>$ ^kɯ<post>/with<pr>$ ^βʑɯ<n><ind>/mouse<n><sg><ind>$ ^ɕa<n><px3sg>/meat<n><sg><px3sg>$ ^tɕi<adv>/also<adv>$ ^rga<v><iv><pii>/like<vblex><pii>$^,<cm>/,<cm>$ ^pɣɤtɕɯ<n><ind>/bird<n><sg><ind>$ ^ɕa<n><px3sg>/meat<n><sg><px3sg>$ ^tɕi<adv>/also<adv>$ ^rga<v><iv><pii>/like<vblex><pii>$ ^ɕti<v><iv>/be<vbser>$ ^tɕe<cnj>//as for<pr>$^.<sent>/.<sent>$^.<sent>/.<sent>$
</pre>

Output of jya-eng:
<pre>
#cat that with #mouse #meat also #like, #bird #meat also #like #be .
</pre>

====#10====
The original sentence:
<pre>
tɕe nɯ maʁ nɤ tɕe, βʑɯ nɯ kɯ wuma kɤrɤfsoʁ pjɤcha tɕe
</pre>

The intended English translation: since then, that mouse was very good at accumulating food

Output of jya-eng-biltrans:
<pre>
^tɕe<cnj>//as for<pr>$ ^nɯ maʁ nɤ<cnj>/or<cnjcoo>$ ^tɕe<cnj>//as for<pr>$^,<cm>/,<cm>$ ^βʑɯ<n><ind>/mouse<n><sg><ind>$ ^nɯ<dem>/that<det><dem><sg>$ ^kɯ<post>/with<pr>$ ^wuma<adv>/very<adv>$ ^rɤfsoʁ<v><iv><prc><obj><ind>/forage<vblex><prc><obj><ind>$ ^cha<v><iv><pii>/able<adj><pii>/can<vbmod><pii>$ ^tɕe<cnj>//as for<pr>$^.<sent>/.<sent>$
</pre>

Output of jya-eng:
<pre>
or , #mouse that with very #forage #able
</pre>

===Additions ===
These are some additions we made to our bilingual transducer beyond the labs.

* 5000+ lemmas to our Japhug transducer

* 5 new features covered in our Japhug morphological analyzer, including: imperfective prefixes, the peg circumfix, proximal/distal demonstratives, redesigned verb patterns to match the slot-based prefix system in Japhug, number suffixes on verbs.

* 2 new structural transfer rules: NP rule to combine nouns and possessed nouns; DP rule to place determiner before noun, and to take ergative case from postposition; vP rule to combine adverbs and verbs. These were made in the process of meeting our original goal, to match the SVO word order in English (Japhug is usually SOV or OSV)

(details listed for our own reference)

===Final evaluation===

Monolingual transducer stats:
*Updated precision and recall against the (updated) eval.test and eval.gold files:
<pre>
ERROR: different number of annotated (5019) and test (5059) cohorts; check these: pjɯ́wɣzɣɤtɕa, ，, #, \, \{, \}, @, &, gt;dongdong&lt, gt;you&lt, ɲɯŋul, .., nɯ maʁ nɤ, ..., pjɯ́wɣzɣɤtɕa，, , ɲɯŋu，, gt, lt, you
</pre>
*Coverage over the large corpus:
<pre>
TOP UNKNOWN WORDS:
16 ^ɣɯ/*ɣɯ$
14 ^lɤβzaŋ/*lɤβzaŋ$
11 ^cho/*cho$
10 ^qartshɤs/*qartshɤs$
8 ^rɟɤlpu/*rɟɤlpu$
8 ^rcanɯ/*rcanɯ$
8 ^qhe/*qhe$
8 ^je/*je$
8 ^jamɤn/*jamɤn$
7 ^tɕɤn/*tɕɤn$
6 ^nɯmbala/*nɯmbala$
6 ^ndɤ/*ndɤ$
6 ^lɤari/*lɤari$
6 ^kɯki/*kɯki$
5 ^wo/*wo$
5 ^tɯɣjɤn/*tɯɣjɤn$
5 ^lɤɣe/*lɤɣe$
5 ^kɯsthɯci/*kɯsthɯci$
5 ^ciŋglɯɣ/*ciŋglɯɣ$
4 ^ɲɯsɯsɤm/*ɲɯsɯsɤm$
coverage: 4463 / 5019 (~0.88922096035066746364)
remaining unknown forms: 556
ambiguity: 9939 / 5019 (~1.98027495517035265989)
jya.corpus Mon May 8 02:13:49 PM EDT 2023 4463/5019 ~0.88922096035066746364 \| 9939/5019 ~1.98027495517035265989
</pre>
*The number of words in the large corpus: 3999
*The number of stems in the transducer): 6646

MT in jya-eng stats:
*WER and PER over longer corpus:
*The proportion of stems translated correctly in the longer corpus:
*Trimmed coverage over longer and large corpora:
*The number of tokens in longer and large corpora:

[[Category:Sp23_TranslationPairs ]] [[Category: Japhug]]

Japhug/Japhug and English

2023-05-08T18:35:24Z

Ylhamo1: /* Final evaluation */

==Resources for machine translation between [https://wikis.swarthmore.edu/ling073/Category:Japhug Japhug] and English==

===Developed resources===

[https://github.swarthmore.edu/Ling073-sp23/ling073-jya-eng-corpus Japhug-English corpus]

[https://wikis.swarthmore.edu/ling073/Japhug_and_English/Lexical_selection#jya_.E2.86.92_eng Lexical selection]

==External resources==
[https://github.swarthmore.edu/Ling073-sp23/ling073-jya-eng Apertium language pair for translating between Jiarong and English]

[https://github.swarthmore.edu/Ling073-sp23/ling073-jya Monolingual Japhug transducer]

==Jya → Eng evaluation ==

coverage (number of forms analysed) of Japhug transducer on jya.sentences.txt: 76.98 %

coverage of bilingual transducer (jya-eng.automorf.bin) on the same file: 28.61 %

===10 sentences:===

====#1====
The original sentence:
<pre>
kɯɕɯŋgɯ tɕe, nɤki, lɯlu ci pjɤtu, tɕendɤre βʑɯ ci pjɤtu
</pre>
The intended English translation: A long time ago, there was a cat and a mouse

Output of jya-eng-biltrans:
<pre>
^kɯɕɯŋgɯ<n><ind>/long time ago<cnjadv><ind>$ ^tɕe<cnj>//as for<pr>$^,<cm>/,<cm>$ ^nɤki<dem>/that<det><dem><sg>$^,<cm>/,<cm>$ ^lɯlu<n><ind>/cat<n><sg><ind>$ ^ci<det>/a<det><ind><sg>/one<num><sg>$ ^pjɤtu<cop><other>/be<vbser><other>$^,<cm>/,<cm>$ ^tɕendɤre<cnj>/then<cnjadv>$ ^βʑɯ<n><ind>/mouse<n><sg><ind>$ ^ci<det>/a<det><ind><sg>/one<num><sg>$ ^pjɤtu<cop><other>/be<vbser><other>$^.<sent>/.<sent>$
</pre>

Output of jya-eng:
<pre>
#long time ago , that, #cat a #be, then #mouse a #be
</pre>

====#2====
The original sentence:
<pre>
lɯlu nɯ kɯ nɤkinɯ, βʑɯ ri tundze ɕti
</pre>

The intended English translation: The cat ate the mouse,

Output of jya-eng-biltrans:
<pre>
^lɯlu<n><ind>/cat<n><sg><ind>$ ^nɯ<dem>/that<det><dem><sg>$ ^kɯ<post>/with<pr>$ ^nɤkinɯ<fill>/um<ij>$^,<cm>/,<cm>$ ^βʑɯ<n><ind>/mouse<n><sg><ind>$ ^ri<post>/at<pr>$ ^ndze<v><tv><ipfv>/eat<vblex><ipfv>$ ^ɕti<v><iv>/be<vbser>$^.<sent>/.<sent>$
</pre>

Output of jya-eng:
<pre>
#cat that with um, #mouse at #eat #be
</pre>

====#3====
The original sentence:

<pre>
βʑɯ chondɤre nɤki, kumpɣɤtɕɯ nɯ kɯ βzaŋsa tonɯpandʑi,
</pre>

The intended English translation: The mouse made friends with the sparrow,

Output of jya-eng-biltrans:
<pre>
^βʑɯ<n><ind>/mouse<n><sg><ind>$ ^chondɤre<com>/with<pr>$ ^nɤki<dem>/that<det><dem><sg>$^,<cm>/,<cm>$ ^kumpɣɤtɕɯ<n><ind>/sparrow<n><sg><ind>$ ^nɯ<dem>/that<det><dem><sg>$ ^kɯ<post>/with<pr>$ ^βzaŋsa<n><ind>/friend<n><sg><ind>$ ^tonɯpa<v><tv><du>/made<vblex><pp><du>$^,<cm>/,<cm>$^.<sent>/.<sent>$
</pre>

Output of jya-eng:
<pre>
#mouse with that, #sparrow that with #friend #made,
</pre>

====#4====
The original sentence:
<pre>
tɕe βzaŋsa tonɯpandʑi tɕe, wuma pjɤkɤmɯmindʑici
</pre>

The intended English translation: The two of them become friends and got along well

Output of jya-eng-biltrans:
<pre>
^tɕe<cnj>//as for<pr>$ ^βzaŋsa<n><ind>/friend<n><sg><ind>$ ^tonɯpa<v><tv><du>/made<vblex><pp><du>$ ^tɕe<cnj>//as for<pr>$^,<cm>/,<cm>$ ^wuma<adv>/very<adv>$ ^ɤmɯmi<v><iv><pii><du>/get along well<vblex><pii><du>$^.<sent>/.<sent>$</pre>
Output of jya-eng:
<pre>
#friend #made , very #get along well
</pre>

====#5====
The original sentence:
<pre>
maka cici ŋotɕu jɤarɯrindʑi ʑo tɯtɯrca ntsɯ juɕendʑi pjɤŋu
</pre>
The intended English translation: they always got together

Output of jya-eng-biltrans:
<pre>
^maka<adv>/at all<adv>$ ^cici<adv>/sometimes<adv>$ ^ŋotɕu<prn>/wherever<adv>$ ^*jɤarɯrindʑi/*jɤarɯrindʑi$ ^*ʑo/*ʑo$ ^*tɯtɯrca/*tɯtɯrca$ ^ntsɯ<adv>/always<adv>$ ^*juɕendʑi/*juɕendʑi$ ^ŋu<v><iv><pii>/be<vbser><pii>$^.<sent>/.<sent>$
</pre>
Output of jya-eng:
<pre>
at all sometimes wherever #each together always #go #be
</pre>

====#6====
The original sentence:
<pre>
kɤndza ci tu nɤ pjɯnɯkrondʑi
</pre>
The intended English translation: There was food to eat, they shared,

Output of jya-eng-biltrans:
<pre>
^kɤndza<n><ind>/food<n><sg><ind>$ ^ci<det>/a<det><ind><sg>/one<num><sg>$ ^tu<v><iv>/be<vbser>/exist<vblex>$ ^*nɤ/*nɤ$ ^*pjɯnɯkrondʑi/*pjɯnɯkrondʑi$^.<sent>/.<sent>$
</pre>
Output of jya-eng:
<pre>
#food a #be at #share
</pre>

====#7====
The original sentence:
<pre>
nɯ mɤʑɯ kɯmtɕhɯ kɯfse tɤtu nɤ, tɯɣrɤz ɲɯnɤɣrondʑi nɯ ra pjɤŋgrɤl
</pre>

The intended English translation: Also, when there was something to play with, they played together

Output of jya-eng-biltrans:
<pre>
^nɯ<dem>/that<det><dem><sg>$ ^mɤʑɯ<adv>/again<adv>$ ^kɯmtɕhɯ<n><ind>/toy<n><sg><ind>$ ^fse<v><tv><prc><sbj><ind>/resemble<vblex><prc><sbj><ind>$ ^tu<v><iv><aor>/be<vbser><aor>/exist<vblex><aor>$ ^nɤ<post>/at<pr>$^,<cm>/,<cm>$ ^tɯɣrɤz<adv>/together<adv>$ ^nɤɣro<v><tv><ipfv><du>/play<vblex><inf><ipfv><du>$ ^nɯ<dem>/that<det><dem><sg>$ ^ra<v><iv>/should<vbmod>$ ^ŋgrɤl<v><iv><pii>/usually like this<iv><pii>$^.<sent>/.<sent>$
</pre>

Output of jya-eng:
<pre>
that again #toy #resemble #be at, together #play that #should #usually like this
</pre>

====#8====
The original sentence:
<pre>
tɕhi kɤcha tukɤpjɤl kowa ntsɯ tuβzundʑi pjɤŋu tɕe
</pre>

The intended English translation: They were always trying to think of ways to evade that cat

Output of jya-eng-biltrans:
<pre>
^tɕhi<prn>/what<prn>$ ^cha<v><iv><prc><obj><ind>/able<adj><prc><obj><ind>/can<vbmod><prc><obj><ind>$ ^pjɤl<v><tv><inf><ipfv>/evade<vblex><inf><ipfv>$ ^kowa<n><ind>/method<n><sg><ind>$ ^ntsɯ<adv>/always<adv>$ ^βzu<v><tv><ipfv><du>/make<vblex><ipfv><du>$ ^ŋu<v><iv><pii>/be<vbser><pii>$ ^tɕe<cnj>//as for<pr>$^.<sent>/.<sent>$
</pre>

Output of jya-eng:
<pre>
#what #able #evade #method always #make #be
</pre>

====#9====
The original sentence:
<pre>
lɯlu nɯ kɯ βʑɯ ɯɕa tɕi pjɤrga, pɣɤtɕɯ ɯɕa tɕi pjɤrga ɕti tɕe.
</pre>

The intended English translation: The cat likes eating rat meat, and also likes sparrow meat.

Output of jya-eng-biltrans:
<pre>
^lɯlu<n><ind>/cat<n><sg><ind>$ ^nɯ<dem>/that<det><dem><sg>$ ^kɯ<post>/with<pr>$ ^βʑɯ<n><ind>/mouse<n><sg><ind>$ ^ɕa<n><px3sg>/meat<n><sg><px3sg>$ ^tɕi<adv>/also<adv>$ ^rga<v><iv><pii>/like<vblex><pii>$^,<cm>/,<cm>$ ^pɣɤtɕɯ<n><ind>/bird<n><sg><ind>$ ^ɕa<n><px3sg>/meat<n><sg><px3sg>$ ^tɕi<adv>/also<adv>$ ^rga<v><iv><pii>/like<vblex><pii>$ ^ɕti<v><iv>/be<vbser>$ ^tɕe<cnj>//as for<pr>$^.<sent>/.<sent>$^.<sent>/.<sent>$
</pre>

Output of jya-eng:
<pre>
#cat that with #mouse #meat also #like, #bird #meat also #like #be .
</pre>

====#10====
The original sentence:
<pre>
tɕe nɯ maʁ nɤ tɕe, βʑɯ nɯ kɯ wuma kɤrɤfsoʁ pjɤcha tɕe
</pre>

The intended English translation: since then, that mouse was very good at accumulating food

Output of jya-eng-biltrans:
<pre>
^tɕe<cnj>//as for<pr>$ ^nɯ maʁ nɤ<cnj>/or<cnjcoo>$ ^tɕe<cnj>//as for<pr>$^,<cm>/,<cm>$ ^βʑɯ<n><ind>/mouse<n><sg><ind>$ ^nɯ<dem>/that<det><dem><sg>$ ^kɯ<post>/with<pr>$ ^wuma<adv>/very<adv>$ ^rɤfsoʁ<v><iv><prc><obj><ind>/forage<vblex><prc><obj><ind>$ ^cha<v><iv><pii>/able<adj><pii>/can<vbmod><pii>$ ^tɕe<cnj>//as for<pr>$^.<sent>/.<sent>$
</pre>

Output of jya-eng:
<pre>
or , #mouse that with very #forage #able
</pre>

===Additions ===
These are some additions we made to our bilingual transducer beyond the labs.

* 5000+ lemmas to our Japhug transducer

* 5 new features covered in our Japhug morphological analyzer, including: imperfective prefixes, the peg circumfix, proximal/distal demonstratives, redesigned verb patterns to match the slot-based prefix system in Japhug, number suffixes on verbs.

* 2 new structural transfer rules: NP rule to combine nouns and possessed nouns; DP rule to place determiner before noun, and to take ergative case from postposition; vP rule to combine adverbs and verbs. These were made in the process of meeting our original goal, to match the SVO word order in English (Japhug is usually SOV or OSV)

(details listed for our own reference)

===Final evaluation===

Monolingual transducer stats:
*Updated precision and recall against the (updated) eval.test and eval.gold files:
*Coverage over the large corpus:
<pre>
TOP UNKNOWN WORDS:
16 ^ɣɯ/*ɣɯ$
14 ^lɤβzaŋ/*lɤβzaŋ$
11 ^cho/*cho$
10 ^qartshɤs/*qartshɤs$
8 ^rɟɤlpu/*rɟɤlpu$
8 ^rcanɯ/*rcanɯ$
8 ^qhe/*qhe$
8 ^je/*je$
8 ^jamɤn/*jamɤn$
7 ^tɕɤn/*tɕɤn$
6 ^nɯmbala/*nɯmbala$
6 ^ndɤ/*ndɤ$
6 ^lɤari/*lɤari$
6 ^kɯki/*kɯki$
5 ^wo/*wo$
5 ^tɯɣjɤn/*tɯɣjɤn$
5 ^lɤɣe/*lɤɣe$
5 ^kɯsthɯci/*kɯsthɯci$
5 ^ciŋglɯɣ/*ciŋglɯɣ$
4 ^ɲɯsɯsɤm/*ɲɯsɯsɤm$
coverage: 4463 / 5019 (~0.88922096035066746364)
remaining unknown forms: 556
ambiguity: 9939 / 5019 (~1.98027495517035265989)
jya.corpus Mon May 8 02:13:49 PM EDT 2023 4463/5019 ~0.88922096035066746364 \| 9939/5019 ~1.98027495517035265989
</pre>
*The number of words in the large corpus: 3999
*The number of stems in the transducer): 6646

MT in jya-eng stats:
*WER and PER over longer corpus:
*The proportion of stems translated correctly in the longer corpus:
*Trimmed coverage over longer and large corpora:
*The number of tokens in longer and large corpora:

[[Category:Sp23_TranslationPairs ]] [[Category: Japhug]]

Japhug/Japhug and English

2023-05-06T21:31:57Z

Ylhamo1: /* Final evaluation */

==Resources for machine translation between [https://wikis.swarthmore.edu/ling073/Category:Japhug Japhug] and English==

===Developed resources===

[https://github.swarthmore.edu/Ling073-sp23/ling073-jya-eng-corpus Japhug-English corpus]

[https://wikis.swarthmore.edu/ling073/Japhug_and_English/Lexical_selection#jya_.E2.86.92_eng Lexical selection]

==External resources==
[https://github.swarthmore.edu/Ling073-sp23/ling073-jya-eng Apertium language pair for translating between Jiarong and English]

[https://github.swarthmore.edu/Ling073-sp23/ling073-jya Monolingual Japhug transducer]

==Jya → Eng evaluation ==

coverage (number of forms analysed) of Japhug transducer on jya.sentences.txt: 76.98 %

coverage of bilingual transducer (jya-eng.automorf.bin) on the same file: 28.61 %

===10 sentences:===

====#1====
The original sentence:
<pre>
kɯɕɯŋgɯ tɕe, nɤki, lɯlu ci pjɤtu, tɕendɤre βʑɯ ci pjɤtu
</pre>
The intended English translation: A long time ago, there was a cat and a mouse

Output of jya-eng-biltrans:
<pre>
^kɯɕɯŋgɯ<n><ind>/long time ago<cnjadv><ind>$ ^tɕe<cnj>//as for<pr>$^,<cm>/,<cm>$ ^nɤki<dem>/that<det><dem><sg>$^,<cm>/,<cm>$ ^lɯlu<n><ind>/cat<n><sg><ind>$ ^ci<det>/a<det><ind><sg>/one<num><sg>$ ^pjɤtu<cop><other>/be<vbser><other>$^,<cm>/,<cm>$ ^tɕendɤre<cnj>/then<cnjadv>$ ^βʑɯ<n><ind>/mouse<n><sg><ind>$ ^ci<det>/a<det><ind><sg>/one<num><sg>$ ^pjɤtu<cop><other>/be<vbser><other>$^.<sent>/.<sent>$
</pre>

Output of jya-eng:
<pre>
#long time ago , that, #cat a #be, then #mouse a #be
</pre>

====#2====
The original sentence:
<pre>
lɯlu nɯ kɯ nɤkinɯ, βʑɯ ri tundze ɕti
</pre>

The intended English translation: The cat ate the mouse,

Output of jya-eng-biltrans:
<pre>
^lɯlu<n><ind>/cat<n><sg><ind>$ ^nɯ<dem>/that<det><dem><sg>$ ^kɯ<post>/with<pr>$ ^nɤkinɯ<fill>/um<ij>$^,<cm>/,<cm>$ ^βʑɯ<n><ind>/mouse<n><sg><ind>$ ^ri<post>/at<pr>$ ^ndze<v><tv><ipfv>/eat<vblex><ipfv>$ ^ɕti<v><iv>/be<vbser>$^.<sent>/.<sent>$
</pre>

Output of jya-eng:
<pre>
#cat that with um, #mouse at #eat #be
</pre>

====#3====
The original sentence:

<pre>
βʑɯ chondɤre nɤki, kumpɣɤtɕɯ nɯ kɯ βzaŋsa tonɯpandʑi,
</pre>

The intended English translation: The mouse made friends with the sparrow,

Output of jya-eng-biltrans:
<pre>
^βʑɯ<n><ind>/mouse<n><sg><ind>$ ^chondɤre<com>/with<pr>$ ^nɤki<dem>/that<det><dem><sg>$^,<cm>/,<cm>$ ^kumpɣɤtɕɯ<n><ind>/sparrow<n><sg><ind>$ ^nɯ<dem>/that<det><dem><sg>$ ^kɯ<post>/with<pr>$ ^βzaŋsa<n><ind>/friend<n><sg><ind>$ ^tonɯpa<v><tv><du>/made<vblex><pp><du>$^,<cm>/,<cm>$^.<sent>/.<sent>$
</pre>

Output of jya-eng:
<pre>
#mouse with that, #sparrow that with #friend #made,
</pre>

====#4====
The original sentence:
<pre>
tɕe βzaŋsa tonɯpandʑi tɕe, wuma pjɤkɤmɯmindʑici
</pre>

The intended English translation: The two of them become friends and got along well

Output of jya-eng-biltrans:
<pre>
^tɕe<cnj>//as for<pr>$ ^βzaŋsa<n><ind>/friend<n><sg><ind>$ ^tonɯpa<v><tv><du>/made<vblex><pp><du>$ ^tɕe<cnj>//as for<pr>$^,<cm>/,<cm>$ ^wuma<adv>/very<adv>$ ^ɤmɯmi<v><iv><pii><du>/get along well<vblex><pii><du>$^.<sent>/.<sent>$</pre>
Output of jya-eng:
<pre>
#friend #made , very #get along well
</pre>

====#5====
The original sentence:
<pre>
maka cici ŋotɕu jɤarɯrindʑi ʑo tɯtɯrca ntsɯ juɕendʑi pjɤŋu
</pre>
The intended English translation: they always got together

Output of jya-eng-biltrans:
<pre>
^maka<adv>/at all<adv>$ ^cici<adv>/sometimes<adv>$ ^ŋotɕu<prn>/wherever<adv>$ ^*jɤarɯrindʑi/*jɤarɯrindʑi$ ^*ʑo/*ʑo$ ^*tɯtɯrca/*tɯtɯrca$ ^ntsɯ<adv>/always<adv>$ ^*juɕendʑi/*juɕendʑi$ ^ŋu<v><iv><pii>/be<vbser><pii>$^.<sent>/.<sent>$
</pre>
Output of jya-eng:
<pre>
at all sometimes wherever #each together always #go #be
</pre>

====#6====
The original sentence:
<pre>
kɤndza ci tu nɤ pjɯnɯkrondʑi
</pre>
The intended English translation: There was food to eat, they shared,

Output of jya-eng-biltrans:
<pre>
^kɤndza<n><ind>/food<n><sg><ind>$ ^ci<det>/a<det><ind><sg>/one<num><sg>$ ^tu<v><iv>/be<vbser>/exist<vblex>$ ^*nɤ/*nɤ$ ^*pjɯnɯkrondʑi/*pjɯnɯkrondʑi$^.<sent>/.<sent>$
</pre>
Output of jya-eng:
<pre>
#food a #be at #share
</pre>

====#7====
The original sentence:
<pre>
nɯ mɤʑɯ kɯmtɕhɯ kɯfse tɤtu nɤ, tɯɣrɤz ɲɯnɤɣrondʑi nɯ ra pjɤŋgrɤl
</pre>

The intended English translation: Also, when there was something to play with, they played together

Output of jya-eng-biltrans:
<pre>
^nɯ<dem>/that<det><dem><sg>$ ^mɤʑɯ<adv>/again<adv>$ ^kɯmtɕhɯ<n><ind>/toy<n><sg><ind>$ ^fse<v><tv><prc><sbj><ind>/resemble<vblex><prc><sbj><ind>$ ^tu<v><iv><aor>/be<vbser><aor>/exist<vblex><aor>$ ^nɤ<post>/at<pr>$^,<cm>/,<cm>$ ^tɯɣrɤz<adv>/together<adv>$ ^nɤɣro<v><tv><ipfv><du>/play<vblex><inf><ipfv><du>$ ^nɯ<dem>/that<det><dem><sg>$ ^ra<v><iv>/should<vbmod>$ ^ŋgrɤl<v><iv><pii>/usually like this<iv><pii>$^.<sent>/.<sent>$
</pre>

Output of jya-eng:
<pre>
that again #toy #resemble #be at, together #play that #should #usually like this
</pre>

====#8====
The original sentence:
<pre>
tɕhi kɤcha tukɤpjɤl kowa ntsɯ tuβzundʑi pjɤŋu tɕe
</pre>

The intended English translation: They were always trying to think of ways to evade that cat

Output of jya-eng-biltrans:
<pre>
^tɕhi<prn>/what<prn>$ ^cha<v><iv><prc><obj><ind>/able<adj><prc><obj><ind>/can<vbmod><prc><obj><ind>$ ^pjɤl<v><tv><inf><ipfv>/evade<vblex><inf><ipfv>$ ^kowa<n><ind>/method<n><sg><ind>$ ^ntsɯ<adv>/always<adv>$ ^βzu<v><tv><ipfv><du>/make<vblex><ipfv><du>$ ^ŋu<v><iv><pii>/be<vbser><pii>$ ^tɕe<cnj>//as for<pr>$^.<sent>/.<sent>$
</pre>

Output of jya-eng:
<pre>
#what #able #evade #method always #make #be
</pre>

====#9====
The original sentence:
<pre>
lɯlu nɯ kɯ βʑɯ ɯɕa tɕi pjɤrga, pɣɤtɕɯ ɯɕa tɕi pjɤrga ɕti tɕe.
</pre>

The intended English translation: The cat likes eating rat meat, and also likes sparrow meat.

Output of jya-eng-biltrans:
<pre>
^lɯlu<n><ind>/cat<n><sg><ind>$ ^nɯ<dem>/that<det><dem><sg>$ ^kɯ<post>/with<pr>$ ^βʑɯ<n><ind>/mouse<n><sg><ind>$ ^ɕa<n><px3sg>/meat<n><sg><px3sg>$ ^tɕi<adv>/also<adv>$ ^rga<v><iv><pii>/like<vblex><pii>$^,<cm>/,<cm>$ ^pɣɤtɕɯ<n><ind>/bird<n><sg><ind>$ ^ɕa<n><px3sg>/meat<n><sg><px3sg>$ ^tɕi<adv>/also<adv>$ ^rga<v><iv><pii>/like<vblex><pii>$ ^ɕti<v><iv>/be<vbser>$ ^tɕe<cnj>//as for<pr>$^.<sent>/.<sent>$^.<sent>/.<sent>$
</pre>

Output of jya-eng:
<pre>
#cat that with #mouse #meat also #like, #bird #meat also #like #be .
</pre>

====#10====
The original sentence:
<pre>
tɕe nɯ maʁ nɤ tɕe, βʑɯ nɯ kɯ wuma kɤrɤfsoʁ pjɤcha tɕe
</pre>

The intended English translation: since then, that mouse was very good at accumulating food

Output of jya-eng-biltrans:
<pre>
^tɕe<cnj>//as for<pr>$ ^nɯ maʁ nɤ<cnj>/or<cnjcoo>$ ^tɕe<cnj>//as for<pr>$^,<cm>/,<cm>$ ^βʑɯ<n><ind>/mouse<n><sg><ind>$ ^nɯ<dem>/that<det><dem><sg>$ ^kɯ<post>/with<pr>$ ^wuma<adv>/very<adv>$ ^rɤfsoʁ<v><iv><prc><obj><ind>/forage<vblex><prc><obj><ind>$ ^cha<v><iv><pii>/able<adj><pii>/can<vbmod><pii>$ ^tɕe<cnj>//as for<pr>$^.<sent>/.<sent>$
</pre>

Output of jya-eng:
<pre>
or , #mouse that with very #forage #able
</pre>

===Additions ===
These are some additions we made to our bilingual transducer beyond the labs.

* 5000+ lemmas to our Japhug transducer

* 5 new features covered in our Japhug morphological analyzer, including: imperfective prefixes, the peg circumfix, proximal/distal demonstratives, redesigned verb patterns to match the slot-based prefix system in Japhug, number suffixes on verbs.

* 2 new structural transfer rules: NP rule to combine nouns and possessed nouns; DP rule to place determiner before noun, and to take ergative case from postposition; vP rule to combine adverbs and verbs. These were made in the process of meeting our original goal, to match the SVO word order in English (Japhug is usually SOV or OSV)

(details listed for our own reference)

===Final evaluation===

Monolingual transducer stats:
*Updated precision and recall against the (updated) eval.test and eval.gold files:
*Coverage over the large corpus:
*The number of words in the large corpus:
*The number of stems in the transducer:

MT in jya-eng stats:
*WER and PER over longer corpus:
*The proportion of stems translated correctly in the longer corpus:
*Trimmed coverage over longer and large corpora:
*The number of tokens in longer and large corpora:

[[Category:Sp23_TranslationPairs ]] [[Category: Japhug]]

Japhug/Japhug and English

2023-05-06T21:31:41Z

Ylhamo1: /* Final evaluation */

==Resources for machine translation between [https://wikis.swarthmore.edu/ling073/Category:Japhug Japhug] and English==

===Developed resources===

[https://github.swarthmore.edu/Ling073-sp23/ling073-jya-eng-corpus Japhug-English corpus]

[https://wikis.swarthmore.edu/ling073/Japhug_and_English/Lexical_selection#jya_.E2.86.92_eng Lexical selection]

==External resources==
[https://github.swarthmore.edu/Ling073-sp23/ling073-jya-eng Apertium language pair for translating between Jiarong and English]

[https://github.swarthmore.edu/Ling073-sp23/ling073-jya Monolingual Japhug transducer]

==Jya → Eng evaluation ==

coverage (number of forms analysed) of Japhug transducer on jya.sentences.txt: 76.98 %

coverage of bilingual transducer (jya-eng.automorf.bin) on the same file: 28.61 %

===10 sentences:===

====#1====
The original sentence:
<pre>
kɯɕɯŋgɯ tɕe, nɤki, lɯlu ci pjɤtu, tɕendɤre βʑɯ ci pjɤtu
</pre>
The intended English translation: A long time ago, there was a cat and a mouse

Output of jya-eng-biltrans:
<pre>
^kɯɕɯŋgɯ<n><ind>/long time ago<cnjadv><ind>$ ^tɕe<cnj>//as for<pr>$^,<cm>/,<cm>$ ^nɤki<dem>/that<det><dem><sg>$^,<cm>/,<cm>$ ^lɯlu<n><ind>/cat<n><sg><ind>$ ^ci<det>/a<det><ind><sg>/one<num><sg>$ ^pjɤtu<cop><other>/be<vbser><other>$^,<cm>/,<cm>$ ^tɕendɤre<cnj>/then<cnjadv>$ ^βʑɯ<n><ind>/mouse<n><sg><ind>$ ^ci<det>/a<det><ind><sg>/one<num><sg>$ ^pjɤtu<cop><other>/be<vbser><other>$^.<sent>/.<sent>$
</pre>

Output of jya-eng:
<pre>
#long time ago , that, #cat a #be, then #mouse a #be
</pre>

====#2====
The original sentence:
<pre>
lɯlu nɯ kɯ nɤkinɯ, βʑɯ ri tundze ɕti
</pre>

The intended English translation: The cat ate the mouse,

Output of jya-eng-biltrans:
<pre>
^lɯlu<n><ind>/cat<n><sg><ind>$ ^nɯ<dem>/that<det><dem><sg>$ ^kɯ<post>/with<pr>$ ^nɤkinɯ<fill>/um<ij>$^,<cm>/,<cm>$ ^βʑɯ<n><ind>/mouse<n><sg><ind>$ ^ri<post>/at<pr>$ ^ndze<v><tv><ipfv>/eat<vblex><ipfv>$ ^ɕti<v><iv>/be<vbser>$^.<sent>/.<sent>$
</pre>

Output of jya-eng:
<pre>
#cat that with um, #mouse at #eat #be
</pre>

====#3====
The original sentence:

<pre>
βʑɯ chondɤre nɤki, kumpɣɤtɕɯ nɯ kɯ βzaŋsa tonɯpandʑi,
</pre>

The intended English translation: The mouse made friends with the sparrow,

Output of jya-eng-biltrans:
<pre>
^βʑɯ<n><ind>/mouse<n><sg><ind>$ ^chondɤre<com>/with<pr>$ ^nɤki<dem>/that<det><dem><sg>$^,<cm>/,<cm>$ ^kumpɣɤtɕɯ<n><ind>/sparrow<n><sg><ind>$ ^nɯ<dem>/that<det><dem><sg>$ ^kɯ<post>/with<pr>$ ^βzaŋsa<n><ind>/friend<n><sg><ind>$ ^tonɯpa<v><tv><du>/made<vblex><pp><du>$^,<cm>/,<cm>$^.<sent>/.<sent>$
</pre>

Output of jya-eng:
<pre>
#mouse with that, #sparrow that with #friend #made,
</pre>

====#4====
The original sentence:
<pre>
tɕe βzaŋsa tonɯpandʑi tɕe, wuma pjɤkɤmɯmindʑici
</pre>

The intended English translation: The two of them become friends and got along well

Output of jya-eng-biltrans:
<pre>
^tɕe<cnj>//as for<pr>$ ^βzaŋsa<n><ind>/friend<n><sg><ind>$ ^tonɯpa<v><tv><du>/made<vblex><pp><du>$ ^tɕe<cnj>//as for<pr>$^,<cm>/,<cm>$ ^wuma<adv>/very<adv>$ ^ɤmɯmi<v><iv><pii><du>/get along well<vblex><pii><du>$^.<sent>/.<sent>$</pre>
Output of jya-eng:
<pre>
#friend #made , very #get along well
</pre>

====#5====
The original sentence:
<pre>
maka cici ŋotɕu jɤarɯrindʑi ʑo tɯtɯrca ntsɯ juɕendʑi pjɤŋu
</pre>
The intended English translation: they always got together

Output of jya-eng-biltrans:
<pre>
^maka<adv>/at all<adv>$ ^cici<adv>/sometimes<adv>$ ^ŋotɕu<prn>/wherever<adv>$ ^*jɤarɯrindʑi/*jɤarɯrindʑi$ ^*ʑo/*ʑo$ ^*tɯtɯrca/*tɯtɯrca$ ^ntsɯ<adv>/always<adv>$ ^*juɕendʑi/*juɕendʑi$ ^ŋu<v><iv><pii>/be<vbser><pii>$^.<sent>/.<sent>$
</pre>
Output of jya-eng:
<pre>
at all sometimes wherever #each together always #go #be
</pre>

====#6====
The original sentence:
<pre>
kɤndza ci tu nɤ pjɯnɯkrondʑi
</pre>
The intended English translation: There was food to eat, they shared,

Output of jya-eng-biltrans:
<pre>
^kɤndza<n><ind>/food<n><sg><ind>$ ^ci<det>/a<det><ind><sg>/one<num><sg>$ ^tu<v><iv>/be<vbser>/exist<vblex>$ ^*nɤ/*nɤ$ ^*pjɯnɯkrondʑi/*pjɯnɯkrondʑi$^.<sent>/.<sent>$
</pre>
Output of jya-eng:
<pre>
#food a #be at #share
</pre>

====#7====
The original sentence:
<pre>
nɯ mɤʑɯ kɯmtɕhɯ kɯfse tɤtu nɤ, tɯɣrɤz ɲɯnɤɣrondʑi nɯ ra pjɤŋgrɤl
</pre>

The intended English translation: Also, when there was something to play with, they played together

Output of jya-eng-biltrans:
<pre>
^nɯ<dem>/that<det><dem><sg>$ ^mɤʑɯ<adv>/again<adv>$ ^kɯmtɕhɯ<n><ind>/toy<n><sg><ind>$ ^fse<v><tv><prc><sbj><ind>/resemble<vblex><prc><sbj><ind>$ ^tu<v><iv><aor>/be<vbser><aor>/exist<vblex><aor>$ ^nɤ<post>/at<pr>$^,<cm>/,<cm>$ ^tɯɣrɤz<adv>/together<adv>$ ^nɤɣro<v><tv><ipfv><du>/play<vblex><inf><ipfv><du>$ ^nɯ<dem>/that<det><dem><sg>$ ^ra<v><iv>/should<vbmod>$ ^ŋgrɤl<v><iv><pii>/usually like this<iv><pii>$^.<sent>/.<sent>$
</pre>

Output of jya-eng:
<pre>
that again #toy #resemble #be at, together #play that #should #usually like this
</pre>

====#8====
The original sentence:
<pre>
tɕhi kɤcha tukɤpjɤl kowa ntsɯ tuβzundʑi pjɤŋu tɕe
</pre>

The intended English translation: They were always trying to think of ways to evade that cat

Output of jya-eng-biltrans:
<pre>
^tɕhi<prn>/what<prn>$ ^cha<v><iv><prc><obj><ind>/able<adj><prc><obj><ind>/can<vbmod><prc><obj><ind>$ ^pjɤl<v><tv><inf><ipfv>/evade<vblex><inf><ipfv>$ ^kowa<n><ind>/method<n><sg><ind>$ ^ntsɯ<adv>/always<adv>$ ^βzu<v><tv><ipfv><du>/make<vblex><ipfv><du>$ ^ŋu<v><iv><pii>/be<vbser><pii>$ ^tɕe<cnj>//as for<pr>$^.<sent>/.<sent>$
</pre>

Output of jya-eng:
<pre>
#what #able #evade #method always #make #be
</pre>

====#9====
The original sentence:
<pre>
lɯlu nɯ kɯ βʑɯ ɯɕa tɕi pjɤrga, pɣɤtɕɯ ɯɕa tɕi pjɤrga ɕti tɕe.
</pre>

The intended English translation: The cat likes eating rat meat, and also likes sparrow meat.

Output of jya-eng-biltrans:
<pre>
^lɯlu<n><ind>/cat<n><sg><ind>$ ^nɯ<dem>/that<det><dem><sg>$ ^kɯ<post>/with<pr>$ ^βʑɯ<n><ind>/mouse<n><sg><ind>$ ^ɕa<n><px3sg>/meat<n><sg><px3sg>$ ^tɕi<adv>/also<adv>$ ^rga<v><iv><pii>/like<vblex><pii>$^,<cm>/,<cm>$ ^pɣɤtɕɯ<n><ind>/bird<n><sg><ind>$ ^ɕa<n><px3sg>/meat<n><sg><px3sg>$ ^tɕi<adv>/also<adv>$ ^rga<v><iv><pii>/like<vblex><pii>$ ^ɕti<v><iv>/be<vbser>$ ^tɕe<cnj>//as for<pr>$^.<sent>/.<sent>$^.<sent>/.<sent>$
</pre>

Output of jya-eng:
<pre>
#cat that with #mouse #meat also #like, #bird #meat also #like #be .
</pre>

====#10====
The original sentence:
<pre>
tɕe nɯ maʁ nɤ tɕe, βʑɯ nɯ kɯ wuma kɤrɤfsoʁ pjɤcha tɕe
</pre>

The intended English translation: since then, that mouse was very good at accumulating food

Output of jya-eng-biltrans:
<pre>
^tɕe<cnj>//as for<pr>$ ^nɯ maʁ nɤ<cnj>/or<cnjcoo>$ ^tɕe<cnj>//as for<pr>$^,<cm>/,<cm>$ ^βʑɯ<n><ind>/mouse<n><sg><ind>$ ^nɯ<dem>/that<det><dem><sg>$ ^kɯ<post>/with<pr>$ ^wuma<adv>/very<adv>$ ^rɤfsoʁ<v><iv><prc><obj><ind>/forage<vblex><prc><obj><ind>$ ^cha<v><iv><pii>/able<adj><pii>/can<vbmod><pii>$ ^tɕe<cnj>//as for<pr>$^.<sent>/.<sent>$
</pre>

Output of jya-eng:
<pre>
or , #mouse that with very #forage #able
</pre>

===Additions ===
These are some additions we made to our bilingual transducer beyond the labs.

* 5000+ lemmas to our Japhug transducer

* 5 new features covered in our Japhug morphological analyzer, including: imperfective prefixes, the peg circumfix, proximal/distal demonstratives, redesigned verb patterns to match the slot-based prefix system in Japhug, number suffixes on verbs.

* 2 new structural transfer rules: NP rule to combine nouns and possessed nouns; DP rule to place determiner before noun, and to take ergative case from postposition; vP rule to combine adverbs and verbs. These were made in the process of meeting our original goal, to match the SVO word order in English (Japhug is usually SOV or OSV)

(details listed for our own reference)

===Final evaluation===

Monolingual transducer stats:
*Updated precision and recall against the (updated) eval.test and eval.gold files:
*Coverage over the large corpus:
*The number of words in the large corpus:
*The number of stems in the transducer:

MT in jya-eng stats:
WER and PER over longer corpus:
The proportion of stems translated correctly in the longer corpus:
Trimmed coverage over longer and large corpora:
The number of tokens in longer and large corpora:

[[Category:Sp23_TranslationPairs ]] [[Category: Japhug]]

Japhug/Japhug and English

2023-05-06T21:13:37Z

Ylhamo1: /* Final evaluation */

==Resources for machine translation between [https://wikis.swarthmore.edu/ling073/Category:Japhug Japhug] and English==

===Developed resources===

[https://github.swarthmore.edu/Ling073-sp23/ling073-jya-eng-corpus Japhug-English corpus]

[https://wikis.swarthmore.edu/ling073/Japhug_and_English/Lexical_selection#jya_.E2.86.92_eng Lexical selection]

==External resources==
[https://github.swarthmore.edu/Ling073-sp23/ling073-jya-eng Apertium language pair for translating between Jiarong and English]

[https://github.swarthmore.edu/Ling073-sp23/ling073-jya Monolingual Japhug transducer]

==Jya → Eng evaluation ==

coverage (number of forms analysed) of Japhug transducer on jya.sentences.txt: 76.98 %

coverage of bilingual transducer (jya-eng.automorf.bin) on the same file: 28.61 %

===10 sentences:===

====#1====
The original sentence:
<pre>
kɯɕɯŋgɯ tɕe, nɤki, lɯlu ci pjɤtu, tɕendɤre βʑɯ ci pjɤtu
</pre>
The intended English translation: A long time ago, there was a cat and a mouse

Output of jya-eng-biltrans:
<pre>
^kɯɕɯŋgɯ<n><ind>/long time ago<cnjadv><ind>$ ^tɕe<cnj>//as for<pr>$^,<cm>/,<cm>$ ^nɤki<dem>/that<det><dem><sg>$^,<cm>/,<cm>$ ^lɯlu<n><ind>/cat<n><sg><ind>$ ^ci<det>/a<det><ind><sg>/one<num><sg>$ ^pjɤtu<cop><other>/be<vbser><other>$^,<cm>/,<cm>$ ^tɕendɤre<cnj>/then<cnjadv>$ ^βʑɯ<n><ind>/mouse<n><sg><ind>$ ^ci<det>/a<det><ind><sg>/one<num><sg>$ ^pjɤtu<cop><other>/be<vbser><other>$^.<sent>/.<sent>$
</pre>

Output of jya-eng:
<pre>
#long time ago , that, #cat a #be, then #mouse a #be
</pre>

====#2====
The original sentence:
<pre>
lɯlu nɯ kɯ nɤkinɯ, βʑɯ ri tundze ɕti
</pre>

The intended English translation: The cat ate the mouse,

Output of jya-eng-biltrans:
<pre>
^lɯlu<n><ind>/cat<n><sg><ind>$ ^nɯ<dem>/that<det><dem><sg>$ ^kɯ<post>/with<pr>$ ^nɤkinɯ<fill>/um<ij>$^,<cm>/,<cm>$ ^βʑɯ<n><ind>/mouse<n><sg><ind>$ ^ri<post>/at<pr>$ ^ndze<v><tv><ipfv>/eat<vblex><ipfv>$ ^ɕti<v><iv>/be<vbser>$^.<sent>/.<sent>$
</pre>

Output of jya-eng:
<pre>
#cat that with um, #mouse at #eat #be
</pre>

====#3====
The original sentence:

<pre>
βʑɯ chondɤre nɤki, kumpɣɤtɕɯ nɯ kɯ βzaŋsa tonɯpandʑi,
</pre>

The intended English translation: The mouse made friends with the sparrow,

Output of jya-eng-biltrans:
<pre>
^βʑɯ<n><ind>/mouse<n><sg><ind>$ ^chondɤre<com>/with<pr>$ ^nɤki<dem>/that<det><dem><sg>$^,<cm>/,<cm>$ ^kumpɣɤtɕɯ<n><ind>/sparrow<n><sg><ind>$ ^nɯ<dem>/that<det><dem><sg>$ ^kɯ<post>/with<pr>$ ^βzaŋsa<n><ind>/friend<n><sg><ind>$ ^tonɯpa<v><tv><du>/made<vblex><pp><du>$^,<cm>/,<cm>$^.<sent>/.<sent>$
</pre>

Output of jya-eng:
<pre>
#mouse with that, #sparrow that with #friend #made,
</pre>

====#4====
The original sentence:
<pre>
tɕe βzaŋsa tonɯpandʑi tɕe, wuma pjɤkɤmɯmindʑici
</pre>

The intended English translation: The two of them become friends and got along well

Output of jya-eng-biltrans:
<pre>
^tɕe<cnj>//as for<pr>$ ^βzaŋsa<n><ind>/friend<n><sg><ind>$ ^tonɯpa<v><tv><du>/made<vblex><pp><du>$ ^tɕe<cnj>//as for<pr>$^,<cm>/,<cm>$ ^wuma<adv>/very<adv>$ ^ɤmɯmi<v><iv><pii><du>/get along well<vblex><pii><du>$^.<sent>/.<sent>$</pre>
Output of jya-eng:
<pre>
#friend #made , very #get along well
</pre>

====#5====
The original sentence:
<pre>
maka cici ŋotɕu jɤarɯrindʑi ʑo tɯtɯrca ntsɯ juɕendʑi pjɤŋu
</pre>
The intended English translation: they always got together

Output of jya-eng-biltrans:
<pre>
^maka<adv>/at all<adv>$ ^cici<adv>/sometimes<adv>$ ^ŋotɕu<prn>/wherever<adv>$ ^*jɤarɯrindʑi/*jɤarɯrindʑi$ ^*ʑo/*ʑo$ ^*tɯtɯrca/*tɯtɯrca$ ^ntsɯ<adv>/always<adv>$ ^*juɕendʑi/*juɕendʑi$ ^ŋu<v><iv><pii>/be<vbser><pii>$^.<sent>/.<sent>$
</pre>
Output of jya-eng:
<pre>
at all sometimes wherever #each together always #go #be
</pre>

====#6====
The original sentence:
<pre>
kɤndza ci tu nɤ pjɯnɯkrondʑi
</pre>
The intended English translation: There was food to eat, they shared,

Output of jya-eng-biltrans:
<pre>
^kɤndza<n><ind>/food<n><sg><ind>$ ^ci<det>/a<det><ind><sg>/one<num><sg>$ ^tu<v><iv>/be<vbser>/exist<vblex>$ ^*nɤ/*nɤ$ ^*pjɯnɯkrondʑi/*pjɯnɯkrondʑi$^.<sent>/.<sent>$
</pre>
Output of jya-eng:
<pre>
#food a #be at #share
</pre>

====#7====
The original sentence:
<pre>
nɯ mɤʑɯ kɯmtɕhɯ kɯfse tɤtu nɤ, tɯɣrɤz ɲɯnɤɣrondʑi nɯ ra pjɤŋgrɤl
</pre>

The intended English translation: Also, when there was something to play with, they played together

Output of jya-eng-biltrans:
<pre>
^nɯ<dem>/that<det><dem><sg>$ ^mɤʑɯ<adv>/again<adv>$ ^kɯmtɕhɯ<n><ind>/toy<n><sg><ind>$ ^fse<v><tv><prc><sbj><ind>/resemble<vblex><prc><sbj><ind>$ ^tu<v><iv><aor>/be<vbser><aor>/exist<vblex><aor>$ ^nɤ<post>/at<pr>$^,<cm>/,<cm>$ ^tɯɣrɤz<adv>/together<adv>$ ^nɤɣro<v><tv><ipfv><du>/play<vblex><inf><ipfv><du>$ ^nɯ<dem>/that<det><dem><sg>$ ^ra<v><iv>/should<vbmod>$ ^ŋgrɤl<v><iv><pii>/usually like this<iv><pii>$^.<sent>/.<sent>$
</pre>

Output of jya-eng:
<pre>
that again #toy #resemble #be at, together #play that #should #usually like this
</pre>

====#8====
The original sentence:
<pre>
tɕhi kɤcha tukɤpjɤl kowa ntsɯ tuβzundʑi pjɤŋu tɕe
</pre>

The intended English translation: They were always trying to think of ways to evade that cat

Output of jya-eng-biltrans:
<pre>
^tɕhi<prn>/what<prn>$ ^cha<v><iv><prc><obj><ind>/able<adj><prc><obj><ind>/can<vbmod><prc><obj><ind>$ ^pjɤl<v><tv><inf><ipfv>/evade<vblex><inf><ipfv>$ ^kowa<n><ind>/method<n><sg><ind>$ ^ntsɯ<adv>/always<adv>$ ^βzu<v><tv><ipfv><du>/make<vblex><ipfv><du>$ ^ŋu<v><iv><pii>/be<vbser><pii>$ ^tɕe<cnj>//as for<pr>$^.<sent>/.<sent>$
</pre>

Output of jya-eng:
<pre>
#what #able #evade #method always #make #be
</pre>

====#9====
The original sentence:
<pre>
lɯlu nɯ kɯ βʑɯ ɯɕa tɕi pjɤrga, pɣɤtɕɯ ɯɕa tɕi pjɤrga ɕti tɕe.
</pre>

The intended English translation: The cat likes eating rat meat, and also likes sparrow meat.

Output of jya-eng-biltrans:
<pre>
^lɯlu<n><ind>/cat<n><sg><ind>$ ^nɯ<dem>/that<det><dem><sg>$ ^kɯ<post>/with<pr>$ ^βʑɯ<n><ind>/mouse<n><sg><ind>$ ^ɕa<n><px3sg>/meat<n><sg><px3sg>$ ^tɕi<adv>/also<adv>$ ^rga<v><iv><pii>/like<vblex><pii>$^,<cm>/,<cm>$ ^pɣɤtɕɯ<n><ind>/bird<n><sg><ind>$ ^ɕa<n><px3sg>/meat<n><sg><px3sg>$ ^tɕi<adv>/also<adv>$ ^rga<v><iv><pii>/like<vblex><pii>$ ^ɕti<v><iv>/be<vbser>$ ^tɕe<cnj>//as for<pr>$^.<sent>/.<sent>$^.<sent>/.<sent>$
</pre>

Output of jya-eng:
<pre>
#cat that with #mouse #meat also #like, #bird #meat also #like #be .
</pre>

====#10====
The original sentence:
<pre>
tɕe nɯ maʁ nɤ tɕe, βʑɯ nɯ kɯ wuma kɤrɤfsoʁ pjɤcha tɕe
</pre>

The intended English translation: since then, that mouse was very good at accumulating food

Output of jya-eng-biltrans:
<pre>
^tɕe<cnj>//as for<pr>$ ^nɯ maʁ nɤ<cnj>/or<cnjcoo>$ ^tɕe<cnj>//as for<pr>$^,<cm>/,<cm>$ ^βʑɯ<n><ind>/mouse<n><sg><ind>$ ^nɯ<dem>/that<det><dem><sg>$ ^kɯ<post>/with<pr>$ ^wuma<adv>/very<adv>$ ^rɤfsoʁ<v><iv><prc><obj><ind>/forage<vblex><prc><obj><ind>$ ^cha<v><iv><pii>/able<adj><pii>/can<vbmod><pii>$ ^tɕe<cnj>//as for<pr>$^.<sent>/.<sent>$
</pre>

Output of jya-eng:
<pre>
or , #mouse that with very #forage #able
</pre>

===Additions ===
These are some additions we made to our bilingual transducer beyond the labs.

* 5000+ lemmas to our Japhug transducer

* 5 new features covered in our Japhug morphological analyzer, including: imperfective prefixes, the peg circumfix, proximal/distal demonstratives, redesigned verb patterns to match the slot-based prefix system in Japhug, number suffixes on verbs.

* 2 new structural transfer rules: NP rule to combine nouns and possessed nouns; DP rule to place determiner before noun, and to take ergative case from postposition; vP rule to combine adverbs and verbs. These were made in the process of meeting our original goal, to match the SVO word order in English (Japhug is usually SOV or OSV)

(details listed for our own reference)

===Final evaluation===

Monolingual transducer stats:
*Updated precision and recall against the (updated) eval.test and eval.gold files (see Midterm overview#Evaluating your transducer),
*Coverage over the large corpus:
*The number of words in the large corpus:
*The number of stems in the transducer:

[[Category:Sp23_TranslationPairs ]] [[Category: Japhug]]

Japhug/Japhug and English

2023-05-04T19:57:05Z

Ylhamo1:

==Resources for machine translation between [https://wikis.swarthmore.edu/ling073/Category:Japhug Japhug] and English==

===Developed resources===

[https://github.swarthmore.edu/Ling073-sp23/ling073-jya-eng-corpus Japhug-English corpus]

[https://wikis.swarthmore.edu/ling073/Japhug_and_English/Lexical_selection#jya_.E2.86.92_eng Lexical selection]

==External resources==
[https://github.swarthmore.edu/Ling073-sp23/ling073-jya-eng Apertium language pair for translating between Jiarong and English]

[https://github.swarthmore.edu/Ling073-sp23/ling073-jya Monolingual Japhug transducer]

==Jya → Eng evaluation ==

coverage (number of forms analysed) of Japhug transducer on jya.sentences.txt: 76.98 %

coverage of bilingual transducer (jya-eng.automorf.bin) on the same file: 28.61 %

===10 sentences:===

====#1====
The original sentence:
<pre>
kɯɕɯŋgɯ tɕe, nɤki, lɯlu ci pjɤtu, tɕendɤre βʑɯ ci pjɤtu
</pre>
The intended English translation: A long time ago, there was a cat and a mouse

Output of jya-eng-biltrans:
<pre>
^kɯɕɯŋgɯ<n><ind>/long time ago<cnjadv><ind>$ ^tɕe<cnj>//as for<pr>$^,<cm>/,<cm>$ ^nɤki<dem>/that<det><dem><sg>$^,<cm>/,<cm>$ ^lɯlu<n><ind>/cat<n><sg><ind>$ ^ci<det>/a<det><ind><sg>/one<num><sg>$ ^pjɤtu<cop><other>/be<vbser><other>$^,<cm>/,<cm>$ ^tɕendɤre<cnj>/then<cnjadv>$ ^βʑɯ<n><ind>/mouse<n><sg><ind>$ ^ci<det>/a<det><ind><sg>/one<num><sg>$ ^pjɤtu<cop><other>/be<vbser><other>$^.<sent>/.<sent>$
</pre>

Output of jya-eng:
<pre>
#long time ago , that, #cat a #be, then #mouse a #be
</pre>

====#2====
The original sentence:
<pre>
lɯlu nɯ kɯ nɤkinɯ, βʑɯ ri tundze ɕti
</pre>

The intended English translation: The cat ate the mouse,

Output of jya-eng-biltrans:
<pre>
^lɯlu<n><ind>/cat<n><sg><ind>$ ^nɯ<dem>/that<det><dem><sg>$ ^kɯ<post>/with<pr>$ ^nɤkinɯ<fill>/um<ij>$^,<cm>/,<cm>$ ^βʑɯ<n><ind>/mouse<n><sg><ind>$ ^ri<post>/at<pr>$ ^ndze<v><tv><ipfv>/eat<vblex><ipfv>$ ^ɕti<v><iv>/be<vbser>$^.<sent>/.<sent>$
</pre>

Output of jya-eng:
<pre>
#cat that with um, #mouse at #eat #be
</pre>

====#3====
The original sentence:

<pre>
βʑɯ chondɤre nɤki, kumpɣɤtɕɯ nɯ kɯ βzaŋsa tonɯpandʑi,
</pre>

The intended English translation: The mouse made friends with the sparrow,

Output of jya-eng-biltrans:
<pre>
^βʑɯ<n><ind>/mouse<n><sg><ind>$ ^chondɤre<com>/with<pr>$ ^nɤki<dem>/that<det><dem><sg>$^,<cm>/,<cm>$ ^kumpɣɤtɕɯ<n><ind>/sparrow<n><sg><ind>$ ^nɯ<dem>/that<det><dem><sg>$ ^kɯ<post>/with<pr>$ ^βzaŋsa<n><ind>/friend<n><sg><ind>$ ^tonɯpa<v><tv><du>/made<vblex><pp><du>$^,<cm>/,<cm>$^.<sent>/.<sent>$
</pre>

Output of jya-eng:
<pre>
#mouse with that, #sparrow that with #friend #made,
</pre>

====#4====
The original sentence:
<pre>
tɕe βzaŋsa tonɯpandʑi tɕe, wuma pjɤkɤmɯmindʑici
</pre>

The intended English translation: The two of them become friends and got along well

Output of jya-eng-biltrans:
<pre>
^tɕe<cnj>//as for<pr>$ ^βzaŋsa<n><ind>/friend<n><sg><ind>$ ^tonɯpa<v><tv><du>/made<vblex><pp><du>$ ^tɕe<cnj>//as for<pr>$^,<cm>/,<cm>$ ^wuma<adv>/very<adv>$ ^ɤmɯmi<v><iv><pii><du>/get along well<vblex><pii><du>$^.<sent>/.<sent>$</pre>
Output of jya-eng:
<pre>
#friend #made , very #get along well
</pre>

====#5====
The original sentence:
<pre>
maka cici ŋotɕu jɤarɯrindʑi ʑo tɯtɯrca ntsɯ juɕendʑi pjɤŋu
</pre>
The intended English translation: they always got together

Output of jya-eng-biltrans:
<pre>
^maka<adv>/at all<adv>$ ^cici<adv>/sometimes<adv>$ ^ŋotɕu<prn>/wherever<adv>$ ^*jɤarɯrindʑi/*jɤarɯrindʑi$ ^*ʑo/*ʑo$ ^*tɯtɯrca/*tɯtɯrca$ ^ntsɯ<adv>/always<adv>$ ^*juɕendʑi/*juɕendʑi$ ^ŋu<v><iv><pii>/be<vbser><pii>$^.<sent>/.<sent>$
</pre>
Output of jya-eng:
<pre>
at all sometimes wherever #each together always #go #be
</pre>

====#6====
The original sentence:
<pre>
kɤndza ci tu nɤ pjɯnɯkrondʑi
</pre>
The intended English translation: There was food to eat, they shared,

Output of jya-eng-biltrans:
<pre>
^kɤndza<n><ind>/food<n><sg><ind>$ ^ci<det>/a<det><ind><sg>/one<num><sg>$ ^tu<v><iv>/be<vbser>/exist<vblex>$ ^*nɤ/*nɤ$ ^*pjɯnɯkrondʑi/*pjɯnɯkrondʑi$^.<sent>/.<sent>$
</pre>
Output of jya-eng:
<pre>
#food a #be at #share
</pre>

====#7====
The original sentence:
<pre>
nɯ mɤʑɯ kɯmtɕhɯ kɯfse tɤtu nɤ, tɯɣrɤz ɲɯnɤɣrondʑi nɯ ra pjɤŋgrɤl
</pre>

The intended English translation: Also, when there was something to play with, they played together

Output of jya-eng-biltrans:
<pre>
^nɯ<dem>/that<det><dem><sg>$ ^mɤʑɯ<adv>/again<adv>$ ^kɯmtɕhɯ<n><ind>/toy<n><sg><ind>$ ^fse<v><tv><prc><sbj><ind>/resemble<vblex><prc><sbj><ind>$ ^tu<v><iv><aor>/be<vbser><aor>/exist<vblex><aor>$ ^nɤ<post>/at<pr>$^,<cm>/,<cm>$ ^tɯɣrɤz<adv>/together<adv>$ ^nɤɣro<v><tv><ipfv><du>/play<vblex><inf><ipfv><du>$ ^nɯ<dem>/that<det><dem><sg>$ ^ra<v><iv>/should<vbmod>$ ^ŋgrɤl<v><iv><pii>/usually like this<iv><pii>$^.<sent>/.<sent>$
</pre>

Output of jya-eng:
<pre>
that again #toy #resemble #be at, together #play that #should #usually like this
</pre>

====#8====
The original sentence:
<pre>
tɕhi kɤcha tukɤpjɤl kowa ntsɯ tuβzundʑi pjɤŋu tɕe
</pre>

The intended English translation: They were always trying to think of ways to evade that cat

Output of jya-eng-biltrans:
<pre>
^tɕhi<prn>/what<prn>$ ^cha<v><iv><prc><obj><ind>/able<adj><prc><obj><ind>/can<vbmod><prc><obj><ind>$ ^pjɤl<v><tv><inf><ipfv>/evade<vblex><inf><ipfv>$ ^kowa<n><ind>/method<n><sg><ind>$ ^ntsɯ<adv>/always<adv>$ ^βzu<v><tv><ipfv><du>/make<vblex><ipfv><du>$ ^ŋu<v><iv><pii>/be<vbser><pii>$ ^tɕe<cnj>//as for<pr>$^.<sent>/.<sent>$
</pre>

Output of jya-eng:
<pre>
#what #able #evade #method always #make #be
</pre>

====#9====
The original sentence:
<pre>
lɯlu nɯ kɯ βʑɯ ɯɕa tɕi pjɤrga, pɣɤtɕɯ ɯɕa tɕi pjɤrga ɕti tɕe.
</pre>

The intended English translation: The cat likes eating rat meat, and also likes sparrow meat.

Output of jya-eng-biltrans:
<pre>
^lɯlu<n><ind>/cat<n><sg><ind>$ ^nɯ<dem>/that<det><dem><sg>$ ^kɯ<post>/with<pr>$ ^βʑɯ<n><ind>/mouse<n><sg><ind>$ ^ɕa<n><px3sg>/meat<n><sg><px3sg>$ ^tɕi<adv>/also<adv>$ ^rga<v><iv><pii>/like<vblex><pii>$^,<cm>/,<cm>$ ^pɣɤtɕɯ<n><ind>/bird<n><sg><ind>$ ^ɕa<n><px3sg>/meat<n><sg><px3sg>$ ^tɕi<adv>/also<adv>$ ^rga<v><iv><pii>/like<vblex><pii>$ ^ɕti<v><iv>/be<vbser>$ ^tɕe<cnj>//as for<pr>$^.<sent>/.<sent>$^.<sent>/.<sent>$
</pre>

Output of jya-eng:
<pre>
#cat that with #mouse #meat also #like, #bird #meat also #like #be .
</pre>

====#10====
The original sentence:
<pre>
tɕe nɯ maʁ nɤ tɕe, βʑɯ nɯ kɯ wuma kɤrɤfsoʁ pjɤcha tɕe
</pre>

The intended English translation: since then, that mouse was very good at accumulating food

Output of jya-eng-biltrans:
<pre>
^tɕe<cnj>//as for<pr>$ ^nɯ maʁ nɤ<cnj>/or<cnjcoo>$ ^tɕe<cnj>//as for<pr>$^,<cm>/,<cm>$ ^βʑɯ<n><ind>/mouse<n><sg><ind>$ ^nɯ<dem>/that<det><dem><sg>$ ^kɯ<post>/with<pr>$ ^wuma<adv>/very<adv>$ ^rɤfsoʁ<v><iv><prc><obj><ind>/forage<vblex><prc><obj><ind>$ ^cha<v><iv><pii>/able<adj><pii>/can<vbmod><pii>$ ^tɕe<cnj>//as for<pr>$^.<sent>/.<sent>$
</pre>

Output of jya-eng:
<pre>
or , #mouse that with very #forage #able
</pre>

===Additions ===
We added at least 100 more stems in the bilingual dictionary, and...

===Final evaluation===

[[Category:Sp23_TranslationPairs ]] [[Category: Japhug]]

Japhug and English/Structural Transfer

2023-05-04T19:47:36Z

Ylhamo1: /* Post-Evaluation */

= Pre-Evaluation =

'''Statistics About Input Files'''

<pre>
Number of words in reference: 47
Number of words in test: 33
Number of unknown words (marked with a star) in test: 18
Percentage of unknown words: 54.55 %
</pre>

'''Results when removing unknown-word marks (stars)'''

<pre>
Edit distance: 47
Word error rate (WER): 100.00 %
Number of position-independent correct words: 0
Position-independent word error rate (PER): 100.00 %
</pre>

'''Coverage Test on jya.tests.txt in Bilingual Transducer'''
<pre>
TOP UNKNOWN WORDS:
1 ^ʁnɯtɤrtsɯɣ/*ʁnɯtɤrtsɯɣ$
1 ^ɲɯrganɯ/*ɲɯrganɯ$
1 ^ɲɤmtsɯr/*ɲɤmtsɯr$
1 ^ɯʑo/*ɯʑo$
1 ^ɯtaʁ/*ɯtaʁ$
1 ^ɯjme/*ɯjme$
1 ^ɕɤrɯ/*ɕɤrɯ$
1 ^xuexiao/*xuexiao$
1 ^tʂu/*tʂu$
1 ^pɯ́wɣsɯmtoa/*pɯ́wɣsɯmtoa$
1 ^mɯpɯrɤʑia/*mɯpɯrɤʑia$
1 ^mɯpjɤpenɯ/*mɯpjɤpenɯ$
1 ^mɤpe/*mɤpe$
1 ^kɯkɯra/*kɯkɯra$
1 ^kɤzo/*kɤzo$
1 ^khramba/*khramba$
1 ^aʑo/*aʑo$
1 ^ambro/*ambro$
coverage: 24 / 42 (~0.57142857142857142857)
remaining unknown forms: 18
ambiguity: 54 / 42 (~1.28571428571428571429)
</pre>

= (JYA ‣ ENG) Transfer Evaluation =

We implemented [https://wikis.swarthmore.edu/ling073/Japhug_and_English/ContrastiveGrammars Contrastive Grammar] #1: "For clauses with transitive verbs, in Japhug the object generally precedes the verb (and follows the subject). In English however the object follows the verb."

=== Example Sentence 1 ===

'''lɯlu nɯ kɯ βʑɯ ɯɕa tɕi pjɤrga''' outputs '''#that #cat also #like #mouse #meat''' instead of the direct translation #cat that with #mouse #meat also #like.

===== Tagger Output =====
<pre>
^lɯlu<n><ind>$ ^nɯ<det><dem><dist><sg>$ ^kɯ<post>$ ^βʑɯ<n><ind>$ ^ɕa<n><px3sg>$ ^tɕi<adv>$ ^rga<v><tv>$^.<sent>$
</pre>
===== Lex Output =====
<pre>
^lɯlu<n><ind>/cat<n><sg><ind>$ ^nɯ<det><dem><dist><sg>/that<det><dem><sg>$ ^kɯ<post>/with<pr>$ ^βʑɯ<n><ind>/mouse<n><sg><ind>$ ^ɕa<n><px3sg>/meat<n><sg><px3sg>$ ^tɕi<adv>/also<adv>$ ^rga<v><tv>/like<vblex>$^.<sent>/.<sent>$
</pre>
===== Transfer Output =====
<pre>
Applying rule 10 (line 77): ^lɯlu<n><ind>/cat<n><sg><ind>$

Applying rule 12 (line 80): ^default<NP>{^lɯlu<n><ind>/cat<n><sg><ind>$}$

Applying rule 14 (line 83): ^default<dP><CD>{^default<NP>{^lɯlu<n><ind>/cat<n><sg><ind>$}$}$

Applying rule 11 (line 79): ^default<NP>{^lɯlu<n><ind>/cat<n><sg><ind>$}$ ^nɯ<det><dem><dist><sg>/that<det><dem><sg>$

Applying rule 14 (line 83): ^default<dP><CD>{^default<NP>{^lɯlu<n><ind>/cat<n><sg><ind>$}$ ^nɯ<det><dem><dist><sg>/that<det><dem><sg>$}$

Applying rule 13 (line 82): ^default<dP><CD>{^default<NP>{^lɯlu<n><ind>/cat<n><sg><ind>$}$ ^nɯ<det><dem><dist><sg>/that<det><dem><sg>$}$ ^kɯ<post>/with<pr>$

Applying output rule 12 (line 82): default<DP><erg> -> ^default<dP><CD>{^default<NP>{^lɯlu<n><ind>/cat<n><sg><ind>$}$ ^nɯ<det><dem><dist><sg>/that<det><dem><sg>$}$ ^kɯ<post>/with<pr>$

Applying output rule 10 (line 79): default<dP><abs> -> ^default<NP>{^lɯlu<n><ind>/cat<n><sg><ind>$}$ ^nɯ<det><dem><dist><sg>/that<det><dem><sg>$

No rule specified: ^that<det>$

Applying output rule 9 (line 77): default<NP> -> ^lɯlu<n><ind>/cat<n><sg><ind>$

No rule specified: ^cat<n><sg><ind>$

Applying rule 10 (line 77): ^βʑɯ<n><ind>/mouse<n><sg><ind>$

Applying rule 12 (line 80): ^default<NP>{^βʑɯ<n><ind>/mouse<n><sg><ind>$}$

Applying rule 14 (line 83): ^default<dP><CD>{^default<NP>{^βʑɯ<n><ind>/mouse<n><sg><ind>$}$}$

Applying rule 10 (line 77): ^ɕa<n><px3sg>/meat<n><sg><px3sg>$

Applying rule 12 (line 80): ^default<NP>{^ɕa<n><px3sg>/meat<n><sg><px3sg>$}$

Applying rule 14 (line 83): ^default<dP><CD>{^default<NP>{^ɕa<n><px3sg>/meat<n><sg><px3sg>$}$}$

Applying rule 3 (line 70): ^βʑɯ<n><ind>/mouse<n><sg><ind>$ ^ɕa<n><px3sg>/meat<n><sg><px3sg>$

Applying rule 12 (line 80): ^default<NP>{^βʑɯ<n><ind>/mouse<n><sg><ind>$ ^ɕa<n><px3sg>/meat<n><sg><px3sg>$}$

Applying rule 14 (line 83): ^default<dP><CD>{^default<NP>{^βʑɯ<n><ind>/mouse<n><sg><ind>$ ^ɕa<n><px3sg>/meat<n><sg><px3sg>$}$}$

Applying rule 15 (line 88): ^tɕi<adv>/also<adv>$ ^rga<v><tv>/like<vblex>$

Applying rule 17 (line 91): ^default<DP><CD>{^default<dP><CD>{^default<NP>{^ɕa<n><px3sg>/meat<n><sg><px3sg>$}$}$}$ ^default<vP>{^tɕi<adv>/also<adv>$ ^rga<v><tv>/like<vblex>$}$

Applying rule 15 (line 88): ^tɕi<adv>/also<adv>$ ^rga<v><tv>/like<vblex>$

Applying rule 17 (line 91): ^default<DP><CD>{^default<dP><CD>{^default<NP>{^βʑɯ<n><ind>/mouse<n><sg><ind>$ ^ɕa<n><px3sg>/meat<n><sg><px3sg>$}$}$}$ ^default<vP>{^tɕi<adv>/also<adv>$ ^rga<v><tv>/like<vblex>$}$

Applying output rule 16 (line 91): default<S> -> ^default<DP><CD>{^default<dP><CD>{^default<NP>{^βʑɯ<n><ind>/mouse<n><sg><ind>$ ^ɕa<n><px3sg>/meat<n><sg><px3sg>$}$}$}$ ^default<vP>{^tɕi<adv>/also<adv>$ ^rga<v><tv>/like<vblex>$}$

Applying output rule 14 (line 88): default<vP> -> ^tɕi<adv>/also<adv>$ ^rga<v><tv>/like<vblex>$

No rule specified: ^also<adv>$

No rule specified: ^like<vblex>$

Applying output rule 13 (line 83): default<DP><abs> -> ^default<dP><CD>{^default<NP>{^βʑɯ<n><ind>/mouse<n><sg><ind>$ ^ɕa<n><px3sg>/meat<n><sg><px3sg>$}$}$

Applying output rule 11 (line 80): default<dP><abs> -> ^default<NP>{^βʑɯ<n><ind>/mouse<n><sg><ind>$ ^ɕa<n><px3sg>/meat<n><sg><px3sg>$}$

Applying output rule 2 (line 70): default<NP> -> ^βʑɯ<n><ind>/mouse<n><sg><ind>$ ^ɕa<n><px3sg>/meat<n><sg><px3sg>$

No rule specified: ^mouse<n><sg><ind>$

No rule specified: ^meat<n><sg><ind>$

No rule specified: ^.<sent>/.<sent>$
^that<det>$ ^cat<n><sg><ind>$ ^also<adv>$ ^like<vblex>$ ^mouse<n><sg><ind>$ ^meat<n><sg><ind>$^.<sent>$
</pre>
===== JYA-ENG Output =====
<pre>
#that #cat also #like #mouse #meat
</pre>

=== Example Sentence 2 ===

'''βzaŋsa tonɯpandʑi''' outputs '''#agree with #friend''' instead of the direct translation #friend #agree with.

===== Tagger Output =====
<pre>
^βzaŋsa<n><ind>$ ^nɯpa<v><tv>$^.<sent>$
</pre>
===== Lex Output =====
<pre>
^βzaŋsa<n><ind>/friend<n><sg><ind>$ ^nɯpa<v><tv>/agree with<vblex>$^.<sent>/.<sent>$
</pre>
===== Transfer Output =====
<pre>
Applying rule 10 (line 77): ^βzaŋsa<n><ind>/friend<n><sg><ind>$

Applying rule 12 (line 80): ^default<NP>{^βzaŋsa<n><ind>/friend<n><sg><ind>$}$

Applying rule 14 (line 83): ^default<dP><CD>{^default<NP>{^βzaŋsa<n><ind>/friend<n><sg><ind>$}$}$

Applying rule 16 (line 89): ^nɯpa<v><tv>/agree with<vblex>$

Applying rule 17 (line 91): ^default<DP><CD>{^default<dP><CD>{^default<NP>{^βzaŋsa<n><ind>/friend<n><sg><ind>$}$}$}$ ^default<vP>{^nɯpa<v><tv>/agree with<vblex>$}$

Applying output rule 16 (line 91): default<VP> -> ^default<DP><CD>{^default<dP><CD>{^default<NP>{^βzaŋsa<n><ind>/friend<n><sg><ind>$}$}$}$ ^default<vP>{^nɯpa<v><tv>/agree with<vblex>$}$

Applying output rule 15 (line 89): default<vP> -> ^nɯpa<v><tv>/agree with<vblex>$

No rule specified: ^agree with<vblex>$

Applying output rule 13 (line 83): default<DP><abs> -> ^default<dP><CD>{^default<NP>{^βzaŋsa<n><ind>/friend<n><sg><ind>$}$}$

Applying output rule 11 (line 80): default<dP><abs> -> ^default<NP>{^βzaŋsa<n><ind>/friend<n><sg><ind>$}$

Applying output rule 9 (line 77): default<NP> -> ^βzaŋsa<n><ind>/friend<n><sg><ind>$

No rule specified: ^friend<n><sg><ind>$

No rule specified: ^.<sent>/.<sent>$
^agree with<vblex>$ ^friend<n><sg><ind>$^.<sent>$
</pre>
===== JYA-ENG Output =====
<pre>
#agree with #friend
</pre>

Our transfer rule successfully switched the object (friend) with the verb phrase (agree with).

= Post-Evaluation =

'''Statistics About Input Files'''

<pre>
Number of words in reference: 47
Number of words in test: 33
Number of unknown words (marked with a star) in test: 18
Percentage of unknown words: 54.55 %
</pre>

'''Results when removing unknown-word marks (stars)'''

<pre>
Edit distance: 47
Word error rate (WER): 100.00 %
Number of position-independent correct words: 0
Position-independent word error rate (PER): 100.00 %
</pre>

'''Coverage Test on jya.tests.txt in Bilingual Transducer'''
<pre>
TOP UNKNOWN WORDS:
1 ^ʁnɯtɤrtsɯɣ/*ʁnɯtɤrtsɯɣ$
1 ^ɯtaʁ/*ɯtaʁ$
1 ^mɯpɯrɤʑia/*mɯpɯrɤʑia$
1 ^mɯpjɤpenɯ/*mɯpjɤpenɯ$
1 ^kɯkɯra/*kɯkɯra$
1 ^khramba/*khramba$
1 ^aʑo/*aʑo$
coverage: 35 / 42 (~0.83333333333333333333)
remaining unknown forms: 7
ambiguity: 56 / 42 (~1.33333333333333333333)
jya.tests.txt Thu May 4 03:47:08 PM EDT 2023 35/42 ~0.83333333333333333333 \| 56/42 ~1.33333333333333333333
</pre>

[[Category: Japhug]] [[Category: Sp23 StructuralTransfer]]

Japhug and English/Structural Transfer

2023-05-04T19:45:48Z

Ylhamo1: /* Post-Evaluation */

= Pre-Evaluation =

'''Statistics About Input Files'''

<pre>
Number of words in reference: 47
Number of words in test: 33
Number of unknown words (marked with a star) in test: 18
Percentage of unknown words: 54.55 %
</pre>

'''Results when removing unknown-word marks (stars)'''

<pre>
Edit distance: 47
Word error rate (WER): 100.00 %
Number of position-independent correct words: 0
Position-independent word error rate (PER): 100.00 %
</pre>

'''Coverage Test on jya.tests.txt in Bilingual Transducer'''
<pre>
TOP UNKNOWN WORDS:
1 ^ʁnɯtɤrtsɯɣ/*ʁnɯtɤrtsɯɣ$
1 ^ɲɯrganɯ/*ɲɯrganɯ$
1 ^ɲɤmtsɯr/*ɲɤmtsɯr$
1 ^ɯʑo/*ɯʑo$
1 ^ɯtaʁ/*ɯtaʁ$
1 ^ɯjme/*ɯjme$
1 ^ɕɤrɯ/*ɕɤrɯ$
1 ^xuexiao/*xuexiao$
1 ^tʂu/*tʂu$
1 ^pɯ́wɣsɯmtoa/*pɯ́wɣsɯmtoa$
1 ^mɯpɯrɤʑia/*mɯpɯrɤʑia$
1 ^mɯpjɤpenɯ/*mɯpjɤpenɯ$
1 ^mɤpe/*mɤpe$
1 ^kɯkɯra/*kɯkɯra$
1 ^kɤzo/*kɤzo$
1 ^khramba/*khramba$
1 ^aʑo/*aʑo$
1 ^ambro/*ambro$
coverage: 24 / 42 (~0.57142857142857142857)
remaining unknown forms: 18
ambiguity: 54 / 42 (~1.28571428571428571429)
</pre>

= (JYA ‣ ENG) Transfer Evaluation =

We implemented [https://wikis.swarthmore.edu/ling073/Japhug_and_English/ContrastiveGrammars Contrastive Grammar] #1: "For clauses with transitive verbs, in Japhug the object generally precedes the verb (and follows the subject). In English however the object follows the verb."

=== Example Sentence 1 ===

'''lɯlu nɯ kɯ βʑɯ ɯɕa tɕi pjɤrga''' outputs '''#that #cat also #like #mouse #meat''' instead of the direct translation #cat that with #mouse #meat also #like.

===== Tagger Output =====
<pre>
^lɯlu<n><ind>$ ^nɯ<det><dem><dist><sg>$ ^kɯ<post>$ ^βʑɯ<n><ind>$ ^ɕa<n><px3sg>$ ^tɕi<adv>$ ^rga<v><tv>$^.<sent>$
</pre>
===== Lex Output =====
<pre>
^lɯlu<n><ind>/cat<n><sg><ind>$ ^nɯ<det><dem><dist><sg>/that<det><dem><sg>$ ^kɯ<post>/with<pr>$ ^βʑɯ<n><ind>/mouse<n><sg><ind>$ ^ɕa<n><px3sg>/meat<n><sg><px3sg>$ ^tɕi<adv>/also<adv>$ ^rga<v><tv>/like<vblex>$^.<sent>/.<sent>$
</pre>
===== Transfer Output =====
<pre>
Applying rule 10 (line 77): ^lɯlu<n><ind>/cat<n><sg><ind>$

Applying rule 12 (line 80): ^default<NP>{^lɯlu<n><ind>/cat<n><sg><ind>$}$

Applying rule 14 (line 83): ^default<dP><CD>{^default<NP>{^lɯlu<n><ind>/cat<n><sg><ind>$}$}$

Applying rule 11 (line 79): ^default<NP>{^lɯlu<n><ind>/cat<n><sg><ind>$}$ ^nɯ<det><dem><dist><sg>/that<det><dem><sg>$

Applying rule 14 (line 83): ^default<dP><CD>{^default<NP>{^lɯlu<n><ind>/cat<n><sg><ind>$}$ ^nɯ<det><dem><dist><sg>/that<det><dem><sg>$}$

Applying rule 13 (line 82): ^default<dP><CD>{^default<NP>{^lɯlu<n><ind>/cat<n><sg><ind>$}$ ^nɯ<det><dem><dist><sg>/that<det><dem><sg>$}$ ^kɯ<post>/with<pr>$

Applying output rule 12 (line 82): default<DP><erg> -> ^default<dP><CD>{^default<NP>{^lɯlu<n><ind>/cat<n><sg><ind>$}$ ^nɯ<det><dem><dist><sg>/that<det><dem><sg>$}$ ^kɯ<post>/with<pr>$

Applying output rule 10 (line 79): default<dP><abs> -> ^default<NP>{^lɯlu<n><ind>/cat<n><sg><ind>$}$ ^nɯ<det><dem><dist><sg>/that<det><dem><sg>$

No rule specified: ^that<det>$

Applying output rule 9 (line 77): default<NP> -> ^lɯlu<n><ind>/cat<n><sg><ind>$

No rule specified: ^cat<n><sg><ind>$

Applying rule 10 (line 77): ^βʑɯ<n><ind>/mouse<n><sg><ind>$

Applying rule 12 (line 80): ^default<NP>{^βʑɯ<n><ind>/mouse<n><sg><ind>$}$

Applying rule 14 (line 83): ^default<dP><CD>{^default<NP>{^βʑɯ<n><ind>/mouse<n><sg><ind>$}$}$

Applying rule 10 (line 77): ^ɕa<n><px3sg>/meat<n><sg><px3sg>$

Applying rule 12 (line 80): ^default<NP>{^ɕa<n><px3sg>/meat<n><sg><px3sg>$}$

Applying rule 14 (line 83): ^default<dP><CD>{^default<NP>{^ɕa<n><px3sg>/meat<n><sg><px3sg>$}$}$

Applying rule 3 (line 70): ^βʑɯ<n><ind>/mouse<n><sg><ind>$ ^ɕa<n><px3sg>/meat<n><sg><px3sg>$

Applying rule 12 (line 80): ^default<NP>{^βʑɯ<n><ind>/mouse<n><sg><ind>$ ^ɕa<n><px3sg>/meat<n><sg><px3sg>$}$

Applying rule 14 (line 83): ^default<dP><CD>{^default<NP>{^βʑɯ<n><ind>/mouse<n><sg><ind>$ ^ɕa<n><px3sg>/meat<n><sg><px3sg>$}$}$

Applying rule 15 (line 88): ^tɕi<adv>/also<adv>$ ^rga<v><tv>/like<vblex>$

Applying rule 17 (line 91): ^default<DP><CD>{^default<dP><CD>{^default<NP>{^ɕa<n><px3sg>/meat<n><sg><px3sg>$}$}$}$ ^default<vP>{^tɕi<adv>/also<adv>$ ^rga<v><tv>/like<vblex>$}$

Applying rule 15 (line 88): ^tɕi<adv>/also<adv>$ ^rga<v><tv>/like<vblex>$

Applying rule 17 (line 91): ^default<DP><CD>{^default<dP><CD>{^default<NP>{^βʑɯ<n><ind>/mouse<n><sg><ind>$ ^ɕa<n><px3sg>/meat<n><sg><px3sg>$}$}$}$ ^default<vP>{^tɕi<adv>/also<adv>$ ^rga<v><tv>/like<vblex>$}$

Applying output rule 16 (line 91): default<S> -> ^default<DP><CD>{^default<dP><CD>{^default<NP>{^βʑɯ<n><ind>/mouse<n><sg><ind>$ ^ɕa<n><px3sg>/meat<n><sg><px3sg>$}$}$}$ ^default<vP>{^tɕi<adv>/also<adv>$ ^rga<v><tv>/like<vblex>$}$

Applying output rule 14 (line 88): default<vP> -> ^tɕi<adv>/also<adv>$ ^rga<v><tv>/like<vblex>$

No rule specified: ^also<adv>$

No rule specified: ^like<vblex>$

Applying output rule 13 (line 83): default<DP><abs> -> ^default<dP><CD>{^default<NP>{^βʑɯ<n><ind>/mouse<n><sg><ind>$ ^ɕa<n><px3sg>/meat<n><sg><px3sg>$}$}$

Applying output rule 11 (line 80): default<dP><abs> -> ^default<NP>{^βʑɯ<n><ind>/mouse<n><sg><ind>$ ^ɕa<n><px3sg>/meat<n><sg><px3sg>$}$

Applying output rule 2 (line 70): default<NP> -> ^βʑɯ<n><ind>/mouse<n><sg><ind>$ ^ɕa<n><px3sg>/meat<n><sg><px3sg>$

No rule specified: ^mouse<n><sg><ind>$

No rule specified: ^meat<n><sg><ind>$

No rule specified: ^.<sent>/.<sent>$
^that<det>$ ^cat<n><sg><ind>$ ^also<adv>$ ^like<vblex>$ ^mouse<n><sg><ind>$ ^meat<n><sg><ind>$^.<sent>$
</pre>
===== JYA-ENG Output =====
<pre>
#that #cat also #like #mouse #meat
</pre>

=== Example Sentence 2 ===

'''βzaŋsa tonɯpandʑi''' outputs '''#agree with #friend''' instead of the direct translation #friend #agree with.

===== Tagger Output =====
<pre>
^βzaŋsa<n><ind>$ ^nɯpa<v><tv>$^.<sent>$
</pre>
===== Lex Output =====
<pre>
^βzaŋsa<n><ind>/friend<n><sg><ind>$ ^nɯpa<v><tv>/agree with<vblex>$^.<sent>/.<sent>$
</pre>
===== Transfer Output =====
<pre>
Applying rule 10 (line 77): ^βzaŋsa<n><ind>/friend<n><sg><ind>$

Applying rule 12 (line 80): ^default<NP>{^βzaŋsa<n><ind>/friend<n><sg><ind>$}$

Applying rule 14 (line 83): ^default<dP><CD>{^default<NP>{^βzaŋsa<n><ind>/friend<n><sg><ind>$}$}$

Applying rule 16 (line 89): ^nɯpa<v><tv>/agree with<vblex>$

Applying rule 17 (line 91): ^default<DP><CD>{^default<dP><CD>{^default<NP>{^βzaŋsa<n><ind>/friend<n><sg><ind>$}$}$}$ ^default<vP>{^nɯpa<v><tv>/agree with<vblex>$}$

Applying output rule 16 (line 91): default<VP> -> ^default<DP><CD>{^default<dP><CD>{^default<NP>{^βzaŋsa<n><ind>/friend<n><sg><ind>$}$}$}$ ^default<vP>{^nɯpa<v><tv>/agree with<vblex>$}$

Applying output rule 15 (line 89): default<vP> -> ^nɯpa<v><tv>/agree with<vblex>$

No rule specified: ^agree with<vblex>$

Applying output rule 13 (line 83): default<DP><abs> -> ^default<dP><CD>{^default<NP>{^βzaŋsa<n><ind>/friend<n><sg><ind>$}$}$

Applying output rule 11 (line 80): default<dP><abs> -> ^default<NP>{^βzaŋsa<n><ind>/friend<n><sg><ind>$}$

Applying output rule 9 (line 77): default<NP> -> ^βzaŋsa<n><ind>/friend<n><sg><ind>$

No rule specified: ^friend<n><sg><ind>$

No rule specified: ^.<sent>/.<sent>$
^agree with<vblex>$ ^friend<n><sg><ind>$^.<sent>$
</pre>
===== JYA-ENG Output =====
<pre>
#agree with #friend
</pre>

Our transfer rule successfully switched the object (friend) with the verb phrase (agree with).

= Post-Evaluation =

'''Statistics About Input Files'''

<pre>
Number of words in reference: 47
Number of words in test: 33
Number of unknown words (marked with a star) in test: 18
Percentage of unknown words: 54.55 %
</pre>

'''Results when removing unknown-word marks (stars)'''

<pre>
Edit distance: 47
Word error rate (WER): 100.00 %
Number of position-independent correct words: 0
Position-independent word error rate (PER): 100.00 %
</pre>

'''Coverage Test on jya.tests.txt in Bilingual Transducer'''
<pre>

</pre>

[[Category: Japhug]] [[Category: Sp23 StructuralTransfer]]

Japhug and English/Structural Transfer

2023-05-04T19:45:30Z

Ylhamo1: /* Post-Evaluation */

= Pre-Evaluation =

'''Statistics About Input Files'''

<pre>
Number of words in reference: 47
Number of words in test: 33
Number of unknown words (marked with a star) in test: 18
Percentage of unknown words: 54.55 %
</pre>

'''Results when removing unknown-word marks (stars)'''

<pre>
Edit distance: 47
Word error rate (WER): 100.00 %
Number of position-independent correct words: 0
Position-independent word error rate (PER): 100.00 %
</pre>

'''Coverage Test on jya.tests.txt in Bilingual Transducer'''
<pre>
TOP UNKNOWN WORDS:
1 ^ʁnɯtɤrtsɯɣ/*ʁnɯtɤrtsɯɣ$
1 ^ɲɯrganɯ/*ɲɯrganɯ$
1 ^ɲɤmtsɯr/*ɲɤmtsɯr$
1 ^ɯʑo/*ɯʑo$
1 ^ɯtaʁ/*ɯtaʁ$
1 ^ɯjme/*ɯjme$
1 ^ɕɤrɯ/*ɕɤrɯ$
1 ^xuexiao/*xuexiao$
1 ^tʂu/*tʂu$
1 ^pɯ́wɣsɯmtoa/*pɯ́wɣsɯmtoa$
1 ^mɯpɯrɤʑia/*mɯpɯrɤʑia$
1 ^mɯpjɤpenɯ/*mɯpjɤpenɯ$
1 ^mɤpe/*mɤpe$
1 ^kɯkɯra/*kɯkɯra$
1 ^kɤzo/*kɤzo$
1 ^khramba/*khramba$
1 ^aʑo/*aʑo$
1 ^ambro/*ambro$
coverage: 24 / 42 (~0.57142857142857142857)
remaining unknown forms: 18
ambiguity: 54 / 42 (~1.28571428571428571429)
</pre>

= (JYA ‣ ENG) Transfer Evaluation =

We implemented [https://wikis.swarthmore.edu/ling073/Japhug_and_English/ContrastiveGrammars Contrastive Grammar] #1: "For clauses with transitive verbs, in Japhug the object generally precedes the verb (and follows the subject). In English however the object follows the verb."

=== Example Sentence 1 ===

'''lɯlu nɯ kɯ βʑɯ ɯɕa tɕi pjɤrga''' outputs '''#that #cat also #like #mouse #meat''' instead of the direct translation #cat that with #mouse #meat also #like.

===== Tagger Output =====
<pre>
^lɯlu<n><ind>$ ^nɯ<det><dem><dist><sg>$ ^kɯ<post>$ ^βʑɯ<n><ind>$ ^ɕa<n><px3sg>$ ^tɕi<adv>$ ^rga<v><tv>$^.<sent>$
</pre>
===== Lex Output =====
<pre>
^lɯlu<n><ind>/cat<n><sg><ind>$ ^nɯ<det><dem><dist><sg>/that<det><dem><sg>$ ^kɯ<post>/with<pr>$ ^βʑɯ<n><ind>/mouse<n><sg><ind>$ ^ɕa<n><px3sg>/meat<n><sg><px3sg>$ ^tɕi<adv>/also<adv>$ ^rga<v><tv>/like<vblex>$^.<sent>/.<sent>$
</pre>
===== Transfer Output =====
<pre>
Applying rule 10 (line 77): ^lɯlu<n><ind>/cat<n><sg><ind>$

Applying rule 12 (line 80): ^default<NP>{^lɯlu<n><ind>/cat<n><sg><ind>$}$

Applying rule 14 (line 83): ^default<dP><CD>{^default<NP>{^lɯlu<n><ind>/cat<n><sg><ind>$}$}$

Applying rule 11 (line 79): ^default<NP>{^lɯlu<n><ind>/cat<n><sg><ind>$}$ ^nɯ<det><dem><dist><sg>/that<det><dem><sg>$

Applying rule 14 (line 83): ^default<dP><CD>{^default<NP>{^lɯlu<n><ind>/cat<n><sg><ind>$}$ ^nɯ<det><dem><dist><sg>/that<det><dem><sg>$}$

Applying rule 13 (line 82): ^default<dP><CD>{^default<NP>{^lɯlu<n><ind>/cat<n><sg><ind>$}$ ^nɯ<det><dem><dist><sg>/that<det><dem><sg>$}$ ^kɯ<post>/with<pr>$

Applying output rule 12 (line 82): default<DP><erg> -> ^default<dP><CD>{^default<NP>{^lɯlu<n><ind>/cat<n><sg><ind>$}$ ^nɯ<det><dem><dist><sg>/that<det><dem><sg>$}$ ^kɯ<post>/with<pr>$

Applying output rule 10 (line 79): default<dP><abs> -> ^default<NP>{^lɯlu<n><ind>/cat<n><sg><ind>$}$ ^nɯ<det><dem><dist><sg>/that<det><dem><sg>$

No rule specified: ^that<det>$

Applying output rule 9 (line 77): default<NP> -> ^lɯlu<n><ind>/cat<n><sg><ind>$

No rule specified: ^cat<n><sg><ind>$

Applying rule 10 (line 77): ^βʑɯ<n><ind>/mouse<n><sg><ind>$

Applying rule 12 (line 80): ^default<NP>{^βʑɯ<n><ind>/mouse<n><sg><ind>$}$

Applying rule 14 (line 83): ^default<dP><CD>{^default<NP>{^βʑɯ<n><ind>/mouse<n><sg><ind>$}$}$

Applying rule 10 (line 77): ^ɕa<n><px3sg>/meat<n><sg><px3sg>$

Applying rule 12 (line 80): ^default<NP>{^ɕa<n><px3sg>/meat<n><sg><px3sg>$}$

Applying rule 14 (line 83): ^default<dP><CD>{^default<NP>{^ɕa<n><px3sg>/meat<n><sg><px3sg>$}$}$

Applying rule 3 (line 70): ^βʑɯ<n><ind>/mouse<n><sg><ind>$ ^ɕa<n><px3sg>/meat<n><sg><px3sg>$

Applying rule 12 (line 80): ^default<NP>{^βʑɯ<n><ind>/mouse<n><sg><ind>$ ^ɕa<n><px3sg>/meat<n><sg><px3sg>$}$

Applying rule 14 (line 83): ^default<dP><CD>{^default<NP>{^βʑɯ<n><ind>/mouse<n><sg><ind>$ ^ɕa<n><px3sg>/meat<n><sg><px3sg>$}$}$

Applying rule 15 (line 88): ^tɕi<adv>/also<adv>$ ^rga<v><tv>/like<vblex>$

Applying rule 17 (line 91): ^default<DP><CD>{^default<dP><CD>{^default<NP>{^ɕa<n><px3sg>/meat<n><sg><px3sg>$}$}$}$ ^default<vP>{^tɕi<adv>/also<adv>$ ^rga<v><tv>/like<vblex>$}$

Applying rule 15 (line 88): ^tɕi<adv>/also<adv>$ ^rga<v><tv>/like<vblex>$

Applying rule 17 (line 91): ^default<DP><CD>{^default<dP><CD>{^default<NP>{^βʑɯ<n><ind>/mouse<n><sg><ind>$ ^ɕa<n><px3sg>/meat<n><sg><px3sg>$}$}$}$ ^default<vP>{^tɕi<adv>/also<adv>$ ^rga<v><tv>/like<vblex>$}$

Applying output rule 16 (line 91): default<S> -> ^default<DP><CD>{^default<dP><CD>{^default<NP>{^βʑɯ<n><ind>/mouse<n><sg><ind>$ ^ɕa<n><px3sg>/meat<n><sg><px3sg>$}$}$}$ ^default<vP>{^tɕi<adv>/also<adv>$ ^rga<v><tv>/like<vblex>$}$

Applying output rule 14 (line 88): default<vP> -> ^tɕi<adv>/also<adv>$ ^rga<v><tv>/like<vblex>$

No rule specified: ^also<adv>$

No rule specified: ^like<vblex>$

Applying output rule 13 (line 83): default<DP><abs> -> ^default<dP><CD>{^default<NP>{^βʑɯ<n><ind>/mouse<n><sg><ind>$ ^ɕa<n><px3sg>/meat<n><sg><px3sg>$}$}$

Applying output rule 11 (line 80): default<dP><abs> -> ^default<NP>{^βʑɯ<n><ind>/mouse<n><sg><ind>$ ^ɕa<n><px3sg>/meat<n><sg><px3sg>$}$

Applying output rule 2 (line 70): default<NP> -> ^βʑɯ<n><ind>/mouse<n><sg><ind>$ ^ɕa<n><px3sg>/meat<n><sg><px3sg>$

No rule specified: ^mouse<n><sg><ind>$

No rule specified: ^meat<n><sg><ind>$

No rule specified: ^.<sent>/.<sent>$
^that<det>$ ^cat<n><sg><ind>$ ^also<adv>$ ^like<vblex>$ ^mouse<n><sg><ind>$ ^meat<n><sg><ind>$^.<sent>$
</pre>
===== JYA-ENG Output =====
<pre>
#that #cat also #like #mouse #meat
</pre>

=== Example Sentence 2 ===

'''βzaŋsa tonɯpandʑi''' outputs '''#agree with #friend''' instead of the direct translation #friend #agree with.

===== Tagger Output =====
<pre>
^βzaŋsa<n><ind>$ ^nɯpa<v><tv>$^.<sent>$
</pre>
===== Lex Output =====
<pre>
^βzaŋsa<n><ind>/friend<n><sg><ind>$ ^nɯpa<v><tv>/agree with<vblex>$^.<sent>/.<sent>$
</pre>
===== Transfer Output =====
<pre>
Applying rule 10 (line 77): ^βzaŋsa<n><ind>/friend<n><sg><ind>$

Applying rule 12 (line 80): ^default<NP>{^βzaŋsa<n><ind>/friend<n><sg><ind>$}$

Applying rule 14 (line 83): ^default<dP><CD>{^default<NP>{^βzaŋsa<n><ind>/friend<n><sg><ind>$}$}$

Applying rule 16 (line 89): ^nɯpa<v><tv>/agree with<vblex>$

Applying rule 17 (line 91): ^default<DP><CD>{^default<dP><CD>{^default<NP>{^βzaŋsa<n><ind>/friend<n><sg><ind>$}$}$}$ ^default<vP>{^nɯpa<v><tv>/agree with<vblex>$}$

Applying output rule 16 (line 91): default<VP> -> ^default<DP><CD>{^default<dP><CD>{^default<NP>{^βzaŋsa<n><ind>/friend<n><sg><ind>$}$}$}$ ^default<vP>{^nɯpa<v><tv>/agree with<vblex>$}$

Applying output rule 15 (line 89): default<vP> -> ^nɯpa<v><tv>/agree with<vblex>$

No rule specified: ^agree with<vblex>$

Applying output rule 13 (line 83): default<DP><abs> -> ^default<dP><CD>{^default<NP>{^βzaŋsa<n><ind>/friend<n><sg><ind>$}$}$

Applying output rule 11 (line 80): default<dP><abs> -> ^default<NP>{^βzaŋsa<n><ind>/friend<n><sg><ind>$}$

Applying output rule 9 (line 77): default<NP> -> ^βzaŋsa<n><ind>/friend<n><sg><ind>$

No rule specified: ^friend<n><sg><ind>$

No rule specified: ^.<sent>/.<sent>$
^agree with<vblex>$ ^friend<n><sg><ind>$^.<sent>$
</pre>
===== JYA-ENG Output =====
<pre>
#agree with #friend
</pre>

Our transfer rule successfully switched the object (friend) with the verb phrase (agree with).

= Post-Evaluation =

'''Statistics About Input Files'''

<pre>
Number of words in reference: 47
Number of words in test: 33
Number of unknown words (marked with a star) in test: 18
Percentage of unknown words: 54.55 %
</pre>

'''Results when removing unknown-word marks (stars)'''

<pre>
Word error rate (WER): 100.00 %
Number of position-independent correct words: 0
Position-independent word error rate (PER): 100.00 %
</pre>

'''Coverage Test on jya.tests.txt in Bilingual Transducer'''
<pre>

</pre>

[[Category: Japhug]] [[Category: Sp23 StructuralTransfer]]

Japhug and English/Structural Transfer

2023-05-04T19:42:57Z

Ylhamo1: /* Example 2 */

= Pre-Evaluation =

'''Statistics About Input Files'''

<pre>
Number of words in reference: 47
Number of words in test: 33
Number of unknown words (marked with a star) in test: 18
Percentage of unknown words: 54.55 %
</pre>

'''Results when removing unknown-word marks (stars)'''

<pre>
Edit distance: 47
Word error rate (WER): 100.00 %
Number of position-independent correct words: 0
Position-independent word error rate (PER): 100.00 %
</pre>

'''Coverage Test on jya.tests.txt in Bilingual Transducer'''
<pre>
TOP UNKNOWN WORDS:
1 ^ʁnɯtɤrtsɯɣ/*ʁnɯtɤrtsɯɣ$
1 ^ɲɯrganɯ/*ɲɯrganɯ$
1 ^ɲɤmtsɯr/*ɲɤmtsɯr$
1 ^ɯʑo/*ɯʑo$
1 ^ɯtaʁ/*ɯtaʁ$
1 ^ɯjme/*ɯjme$
1 ^ɕɤrɯ/*ɕɤrɯ$
1 ^xuexiao/*xuexiao$
1 ^tʂu/*tʂu$
1 ^pɯ́wɣsɯmtoa/*pɯ́wɣsɯmtoa$
1 ^mɯpɯrɤʑia/*mɯpɯrɤʑia$
1 ^mɯpjɤpenɯ/*mɯpjɤpenɯ$
1 ^mɤpe/*mɤpe$
1 ^kɯkɯra/*kɯkɯra$
1 ^kɤzo/*kɤzo$
1 ^khramba/*khramba$
1 ^aʑo/*aʑo$
1 ^ambro/*ambro$
coverage: 24 / 42 (~0.57142857142857142857)
remaining unknown forms: 18
ambiguity: 54 / 42 (~1.28571428571428571429)
</pre>

= (JYA ‣ ENG) Transfer Evaluation =

We implemented [https://wikis.swarthmore.edu/ling073/Japhug_and_English/ContrastiveGrammars Contrastive Grammar] #1: "For clauses with transitive verbs, in Japhug the object generally precedes the verb (and follows the subject). In English however the object follows the verb."

=== Example Sentence 1 ===

'''lɯlu nɯ kɯ βʑɯ ɯɕa tɕi pjɤrga''' outputs '''#that #cat also #like #mouse #meat''' instead of the direct translation #cat that with #mouse #meat also #like.

===== Tagger Output =====
<pre>
^lɯlu<n><ind>$ ^nɯ<det><dem><dist><sg>$ ^kɯ<post>$ ^βʑɯ<n><ind>$ ^ɕa<n><px3sg>$ ^tɕi<adv>$ ^rga<v><tv>$^.<sent>$
</pre>
===== Lex Output =====
<pre>
^lɯlu<n><ind>/cat<n><sg><ind>$ ^nɯ<det><dem><dist><sg>/that<det><dem><sg>$ ^kɯ<post>/with<pr>$ ^βʑɯ<n><ind>/mouse<n><sg><ind>$ ^ɕa<n><px3sg>/meat<n><sg><px3sg>$ ^tɕi<adv>/also<adv>$ ^rga<v><tv>/like<vblex>$^.<sent>/.<sent>$
</pre>
===== Transfer Output =====
<pre>
Applying rule 10 (line 77): ^lɯlu<n><ind>/cat<n><sg><ind>$

Applying rule 12 (line 80): ^default<NP>{^lɯlu<n><ind>/cat<n><sg><ind>$}$

Applying rule 14 (line 83): ^default<dP><CD>{^default<NP>{^lɯlu<n><ind>/cat<n><sg><ind>$}$}$

Applying rule 11 (line 79): ^default<NP>{^lɯlu<n><ind>/cat<n><sg><ind>$}$ ^nɯ<det><dem><dist><sg>/that<det><dem><sg>$

Applying rule 14 (line 83): ^default<dP><CD>{^default<NP>{^lɯlu<n><ind>/cat<n><sg><ind>$}$ ^nɯ<det><dem><dist><sg>/that<det><dem><sg>$}$

Applying rule 13 (line 82): ^default<dP><CD>{^default<NP>{^lɯlu<n><ind>/cat<n><sg><ind>$}$ ^nɯ<det><dem><dist><sg>/that<det><dem><sg>$}$ ^kɯ<post>/with<pr>$

Applying output rule 12 (line 82): default<DP><erg> -> ^default<dP><CD>{^default<NP>{^lɯlu<n><ind>/cat<n><sg><ind>$}$ ^nɯ<det><dem><dist><sg>/that<det><dem><sg>$}$ ^kɯ<post>/with<pr>$

Applying output rule 10 (line 79): default<dP><abs> -> ^default<NP>{^lɯlu<n><ind>/cat<n><sg><ind>$}$ ^nɯ<det><dem><dist><sg>/that<det><dem><sg>$

No rule specified: ^that<det>$

Applying output rule 9 (line 77): default<NP> -> ^lɯlu<n><ind>/cat<n><sg><ind>$

No rule specified: ^cat<n><sg><ind>$

Applying rule 10 (line 77): ^βʑɯ<n><ind>/mouse<n><sg><ind>$

Applying rule 12 (line 80): ^default<NP>{^βʑɯ<n><ind>/mouse<n><sg><ind>$}$

Applying rule 14 (line 83): ^default<dP><CD>{^default<NP>{^βʑɯ<n><ind>/mouse<n><sg><ind>$}$}$

Applying rule 10 (line 77): ^ɕa<n><px3sg>/meat<n><sg><px3sg>$

Applying rule 12 (line 80): ^default<NP>{^ɕa<n><px3sg>/meat<n><sg><px3sg>$}$

Applying rule 14 (line 83): ^default<dP><CD>{^default<NP>{^ɕa<n><px3sg>/meat<n><sg><px3sg>$}$}$

Applying rule 3 (line 70): ^βʑɯ<n><ind>/mouse<n><sg><ind>$ ^ɕa<n><px3sg>/meat<n><sg><px3sg>$

Applying rule 12 (line 80): ^default<NP>{^βʑɯ<n><ind>/mouse<n><sg><ind>$ ^ɕa<n><px3sg>/meat<n><sg><px3sg>$}$

Applying rule 14 (line 83): ^default<dP><CD>{^default<NP>{^βʑɯ<n><ind>/mouse<n><sg><ind>$ ^ɕa<n><px3sg>/meat<n><sg><px3sg>$}$}$

Applying rule 15 (line 88): ^tɕi<adv>/also<adv>$ ^rga<v><tv>/like<vblex>$

Applying rule 17 (line 91): ^default<DP><CD>{^default<dP><CD>{^default<NP>{^ɕa<n><px3sg>/meat<n><sg><px3sg>$}$}$}$ ^default<vP>{^tɕi<adv>/also<adv>$ ^rga<v><tv>/like<vblex>$}$

Applying rule 15 (line 88): ^tɕi<adv>/also<adv>$ ^rga<v><tv>/like<vblex>$

Applying rule 17 (line 91): ^default<DP><CD>{^default<dP><CD>{^default<NP>{^βʑɯ<n><ind>/mouse<n><sg><ind>$ ^ɕa<n><px3sg>/meat<n><sg><px3sg>$}$}$}$ ^default<vP>{^tɕi<adv>/also<adv>$ ^rga<v><tv>/like<vblex>$}$

Applying output rule 16 (line 91): default<S> -> ^default<DP><CD>{^default<dP><CD>{^default<NP>{^βʑɯ<n><ind>/mouse<n><sg><ind>$ ^ɕa<n><px3sg>/meat<n><sg><px3sg>$}$}$}$ ^default<vP>{^tɕi<adv>/also<adv>$ ^rga<v><tv>/like<vblex>$}$

Applying output rule 14 (line 88): default<vP> -> ^tɕi<adv>/also<adv>$ ^rga<v><tv>/like<vblex>$

No rule specified: ^also<adv>$

No rule specified: ^like<vblex>$

Applying output rule 13 (line 83): default<DP><abs> -> ^default<dP><CD>{^default<NP>{^βʑɯ<n><ind>/mouse<n><sg><ind>$ ^ɕa<n><px3sg>/meat<n><sg><px3sg>$}$}$

Applying output rule 11 (line 80): default<dP><abs> -> ^default<NP>{^βʑɯ<n><ind>/mouse<n><sg><ind>$ ^ɕa<n><px3sg>/meat<n><sg><px3sg>$}$

Applying output rule 2 (line 70): default<NP> -> ^βʑɯ<n><ind>/mouse<n><sg><ind>$ ^ɕa<n><px3sg>/meat<n><sg><px3sg>$

No rule specified: ^mouse<n><sg><ind>$

No rule specified: ^meat<n><sg><ind>$

No rule specified: ^.<sent>/.<sent>$
^that<det>$ ^cat<n><sg><ind>$ ^also<adv>$ ^like<vblex>$ ^mouse<n><sg><ind>$ ^meat<n><sg><ind>$^.<sent>$
</pre>
===== JYA-ENG Output =====
<pre>
#that #cat also #like #mouse #meat
</pre>

=== Example Sentence 2 ===

'''βzaŋsa tonɯpandʑi''' outputs '''#agree with #friend''' instead of the direct translation #friend #agree with.

===== Tagger Output =====
<pre>
^βzaŋsa<n><ind>$ ^nɯpa<v><tv>$^.<sent>$
</pre>
===== Lex Output =====
<pre>
^βzaŋsa<n><ind>/friend<n><sg><ind>$ ^nɯpa<v><tv>/agree with<vblex>$^.<sent>/.<sent>$
</pre>
===== Transfer Output =====
<pre>
Applying rule 10 (line 77): ^βzaŋsa<n><ind>/friend<n><sg><ind>$

Applying rule 12 (line 80): ^default<NP>{^βzaŋsa<n><ind>/friend<n><sg><ind>$}$

Applying rule 14 (line 83): ^default<dP><CD>{^default<NP>{^βzaŋsa<n><ind>/friend<n><sg><ind>$}$}$

Applying rule 16 (line 89): ^nɯpa<v><tv>/agree with<vblex>$

Applying rule 17 (line 91): ^default<DP><CD>{^default<dP><CD>{^default<NP>{^βzaŋsa<n><ind>/friend<n><sg><ind>$}$}$}$ ^default<vP>{^nɯpa<v><tv>/agree with<vblex>$}$

Applying output rule 16 (line 91): default<VP> -> ^default<DP><CD>{^default<dP><CD>{^default<NP>{^βzaŋsa<n><ind>/friend<n><sg><ind>$}$}$}$ ^default<vP>{^nɯpa<v><tv>/agree with<vblex>$}$

Applying output rule 15 (line 89): default<vP> -> ^nɯpa<v><tv>/agree with<vblex>$

No rule specified: ^agree with<vblex>$

Applying output rule 13 (line 83): default<DP><abs> -> ^default<dP><CD>{^default<NP>{^βzaŋsa<n><ind>/friend<n><sg><ind>$}$}$

Applying output rule 11 (line 80): default<dP><abs> -> ^default<NP>{^βzaŋsa<n><ind>/friend<n><sg><ind>$}$

Applying output rule 9 (line 77): default<NP> -> ^βzaŋsa<n><ind>/friend<n><sg><ind>$

No rule specified: ^friend<n><sg><ind>$

No rule specified: ^.<sent>/.<sent>$
^agree with<vblex>$ ^friend<n><sg><ind>$^.<sent>$
</pre>
===== JYA-ENG Output =====
<pre>
#agree with #friend
</pre>

Our transfer rule successfully switched the object (friend) with the verb phrase (agree with).

= Post-Evaluation =

'''Statistics About Input Files'''

<pre>

</pre>

'''Results when removing unknown-word marks (stars)'''

<pre>

</pre>

'''Coverage Test on jya.tests.txt in Bilingual Transducer'''
<pre>

</pre>

[[Category: Japhug]] [[Category: Sp23 StructuralTransfer]]

Japhug and English/Structural Transfer

2023-05-04T19:42:48Z

Ylhamo1: /* Example 1 */

= Pre-Evaluation =

'''Statistics About Input Files'''

<pre>
Number of words in reference: 47
Number of words in test: 33
Number of unknown words (marked with a star) in test: 18
Percentage of unknown words: 54.55 %
</pre>

'''Results when removing unknown-word marks (stars)'''

<pre>
Edit distance: 47
Word error rate (WER): 100.00 %
Number of position-independent correct words: 0
Position-independent word error rate (PER): 100.00 %
</pre>

'''Coverage Test on jya.tests.txt in Bilingual Transducer'''
<pre>
TOP UNKNOWN WORDS:
1 ^ʁnɯtɤrtsɯɣ/*ʁnɯtɤrtsɯɣ$
1 ^ɲɯrganɯ/*ɲɯrganɯ$
1 ^ɲɤmtsɯr/*ɲɤmtsɯr$
1 ^ɯʑo/*ɯʑo$
1 ^ɯtaʁ/*ɯtaʁ$
1 ^ɯjme/*ɯjme$
1 ^ɕɤrɯ/*ɕɤrɯ$
1 ^xuexiao/*xuexiao$
1 ^tʂu/*tʂu$
1 ^pɯ́wɣsɯmtoa/*pɯ́wɣsɯmtoa$
1 ^mɯpɯrɤʑia/*mɯpɯrɤʑia$
1 ^mɯpjɤpenɯ/*mɯpjɤpenɯ$
1 ^mɤpe/*mɤpe$
1 ^kɯkɯra/*kɯkɯra$
1 ^kɤzo/*kɤzo$
1 ^khramba/*khramba$
1 ^aʑo/*aʑo$
1 ^ambro/*ambro$
coverage: 24 / 42 (~0.57142857142857142857)
remaining unknown forms: 18
ambiguity: 54 / 42 (~1.28571428571428571429)
</pre>

= (JYA ‣ ENG) Transfer Evaluation =

We implemented [https://wikis.swarthmore.edu/ling073/Japhug_and_English/ContrastiveGrammars Contrastive Grammar] #1: "For clauses with transitive verbs, in Japhug the object generally precedes the verb (and follows the subject). In English however the object follows the verb."

=== Example Sentence 1 ===

'''lɯlu nɯ kɯ βʑɯ ɯɕa tɕi pjɤrga''' outputs '''#that #cat also #like #mouse #meat''' instead of the direct translation #cat that with #mouse #meat also #like.

===== Tagger Output =====
<pre>
^lɯlu<n><ind>$ ^nɯ<det><dem><dist><sg>$ ^kɯ<post>$ ^βʑɯ<n><ind>$ ^ɕa<n><px3sg>$ ^tɕi<adv>$ ^rga<v><tv>$^.<sent>$
</pre>
===== Lex Output =====
<pre>
^lɯlu<n><ind>/cat<n><sg><ind>$ ^nɯ<det><dem><dist><sg>/that<det><dem><sg>$ ^kɯ<post>/with<pr>$ ^βʑɯ<n><ind>/mouse<n><sg><ind>$ ^ɕa<n><px3sg>/meat<n><sg><px3sg>$ ^tɕi<adv>/also<adv>$ ^rga<v><tv>/like<vblex>$^.<sent>/.<sent>$
</pre>
===== Transfer Output =====
<pre>
Applying rule 10 (line 77): ^lɯlu<n><ind>/cat<n><sg><ind>$

Applying rule 12 (line 80): ^default<NP>{^lɯlu<n><ind>/cat<n><sg><ind>$}$

Applying rule 14 (line 83): ^default<dP><CD>{^default<NP>{^lɯlu<n><ind>/cat<n><sg><ind>$}$}$

Applying rule 11 (line 79): ^default<NP>{^lɯlu<n><ind>/cat<n><sg><ind>$}$ ^nɯ<det><dem><dist><sg>/that<det><dem><sg>$

Applying rule 14 (line 83): ^default<dP><CD>{^default<NP>{^lɯlu<n><ind>/cat<n><sg><ind>$}$ ^nɯ<det><dem><dist><sg>/that<det><dem><sg>$}$

Applying rule 13 (line 82): ^default<dP><CD>{^default<NP>{^lɯlu<n><ind>/cat<n><sg><ind>$}$ ^nɯ<det><dem><dist><sg>/that<det><dem><sg>$}$ ^kɯ<post>/with<pr>$

Applying output rule 12 (line 82): default<DP><erg> -> ^default<dP><CD>{^default<NP>{^lɯlu<n><ind>/cat<n><sg><ind>$}$ ^nɯ<det><dem><dist><sg>/that<det><dem><sg>$}$ ^kɯ<post>/with<pr>$

Applying output rule 10 (line 79): default<dP><abs> -> ^default<NP>{^lɯlu<n><ind>/cat<n><sg><ind>$}$ ^nɯ<det><dem><dist><sg>/that<det><dem><sg>$

No rule specified: ^that<det>$

Applying output rule 9 (line 77): default<NP> -> ^lɯlu<n><ind>/cat<n><sg><ind>$

No rule specified: ^cat<n><sg><ind>$

Applying rule 10 (line 77): ^βʑɯ<n><ind>/mouse<n><sg><ind>$

Applying rule 12 (line 80): ^default<NP>{^βʑɯ<n><ind>/mouse<n><sg><ind>$}$

Applying rule 14 (line 83): ^default<dP><CD>{^default<NP>{^βʑɯ<n><ind>/mouse<n><sg><ind>$}$}$

Applying rule 10 (line 77): ^ɕa<n><px3sg>/meat<n><sg><px3sg>$

Applying rule 12 (line 80): ^default<NP>{^ɕa<n><px3sg>/meat<n><sg><px3sg>$}$

Applying rule 14 (line 83): ^default<dP><CD>{^default<NP>{^ɕa<n><px3sg>/meat<n><sg><px3sg>$}$}$

Applying rule 3 (line 70): ^βʑɯ<n><ind>/mouse<n><sg><ind>$ ^ɕa<n><px3sg>/meat<n><sg><px3sg>$

Applying rule 12 (line 80): ^default<NP>{^βʑɯ<n><ind>/mouse<n><sg><ind>$ ^ɕa<n><px3sg>/meat<n><sg><px3sg>$}$

Applying rule 14 (line 83): ^default<dP><CD>{^default<NP>{^βʑɯ<n><ind>/mouse<n><sg><ind>$ ^ɕa<n><px3sg>/meat<n><sg><px3sg>$}$}$

Applying rule 15 (line 88): ^tɕi<adv>/also<adv>$ ^rga<v><tv>/like<vblex>$

Applying rule 17 (line 91): ^default<DP><CD>{^default<dP><CD>{^default<NP>{^ɕa<n><px3sg>/meat<n><sg><px3sg>$}$}$}$ ^default<vP>{^tɕi<adv>/also<adv>$ ^rga<v><tv>/like<vblex>$}$

Applying rule 15 (line 88): ^tɕi<adv>/also<adv>$ ^rga<v><tv>/like<vblex>$

Applying rule 17 (line 91): ^default<DP><CD>{^default<dP><CD>{^default<NP>{^βʑɯ<n><ind>/mouse<n><sg><ind>$ ^ɕa<n><px3sg>/meat<n><sg><px3sg>$}$}$}$ ^default<vP>{^tɕi<adv>/also<adv>$ ^rga<v><tv>/like<vblex>$}$

Applying output rule 16 (line 91): default<S> -> ^default<DP><CD>{^default<dP><CD>{^default<NP>{^βʑɯ<n><ind>/mouse<n><sg><ind>$ ^ɕa<n><px3sg>/meat<n><sg><px3sg>$}$}$}$ ^default<vP>{^tɕi<adv>/also<adv>$ ^rga<v><tv>/like<vblex>$}$

Applying output rule 14 (line 88): default<vP> -> ^tɕi<adv>/also<adv>$ ^rga<v><tv>/like<vblex>$

No rule specified: ^also<adv>$

No rule specified: ^like<vblex>$

Applying output rule 13 (line 83): default<DP><abs> -> ^default<dP><CD>{^default<NP>{^βʑɯ<n><ind>/mouse<n><sg><ind>$ ^ɕa<n><px3sg>/meat<n><sg><px3sg>$}$}$

Applying output rule 11 (line 80): default<dP><abs> -> ^default<NP>{^βʑɯ<n><ind>/mouse<n><sg><ind>$ ^ɕa<n><px3sg>/meat<n><sg><px3sg>$}$

Applying output rule 2 (line 70): default<NP> -> ^βʑɯ<n><ind>/mouse<n><sg><ind>$ ^ɕa<n><px3sg>/meat<n><sg><px3sg>$

No rule specified: ^mouse<n><sg><ind>$

No rule specified: ^meat<n><sg><ind>$

No rule specified: ^.<sent>/.<sent>$
^that<det>$ ^cat<n><sg><ind>$ ^also<adv>$ ^like<vblex>$ ^mouse<n><sg><ind>$ ^meat<n><sg><ind>$^.<sent>$
</pre>
===== JYA-ENG Output =====
<pre>
#that #cat also #like #mouse #meat
</pre>

=== Example 2 ===

'''βzaŋsa tonɯpandʑi''' outputs '''#agree with #friend''' instead of the direct translation #friend #agree with.

===== Tagger Output =====
<pre>
^βzaŋsa<n><ind>$ ^nɯpa<v><tv>$^.<sent>$
</pre>
===== Lex Output =====
<pre>
^βzaŋsa<n><ind>/friend<n><sg><ind>$ ^nɯpa<v><tv>/agree with<vblex>$^.<sent>/.<sent>$
</pre>
===== Transfer Output =====
<pre>
Applying rule 10 (line 77): ^βzaŋsa<n><ind>/friend<n><sg><ind>$

Applying rule 12 (line 80): ^default<NP>{^βzaŋsa<n><ind>/friend<n><sg><ind>$}$

Applying rule 14 (line 83): ^default<dP><CD>{^default<NP>{^βzaŋsa<n><ind>/friend<n><sg><ind>$}$}$

Applying rule 16 (line 89): ^nɯpa<v><tv>/agree with<vblex>$

Applying rule 17 (line 91): ^default<DP><CD>{^default<dP><CD>{^default<NP>{^βzaŋsa<n><ind>/friend<n><sg><ind>$}$}$}$ ^default<vP>{^nɯpa<v><tv>/agree with<vblex>$}$

Applying output rule 16 (line 91): default<VP> -> ^default<DP><CD>{^default<dP><CD>{^default<NP>{^βzaŋsa<n><ind>/friend<n><sg><ind>$}$}$}$ ^default<vP>{^nɯpa<v><tv>/agree with<vblex>$}$

Applying output rule 15 (line 89): default<vP> -> ^nɯpa<v><tv>/agree with<vblex>$

No rule specified: ^agree with<vblex>$

Applying output rule 13 (line 83): default<DP><abs> -> ^default<dP><CD>{^default<NP>{^βzaŋsa<n><ind>/friend<n><sg><ind>$}$}$

Applying output rule 11 (line 80): default<dP><abs> -> ^default<NP>{^βzaŋsa<n><ind>/friend<n><sg><ind>$}$

Applying output rule 9 (line 77): default<NP> -> ^βzaŋsa<n><ind>/friend<n><sg><ind>$

No rule specified: ^friend<n><sg><ind>$

No rule specified: ^.<sent>/.<sent>$
^agree with<vblex>$ ^friend<n><sg><ind>$^.<sent>$
</pre>
===== JYA-ENG Output =====
<pre>
#agree with #friend
</pre>

Our transfer rule successfully switched the object (friend) with the verb phrase (agree with).

= Post-Evaluation =

'''Statistics About Input Files'''

<pre>

</pre>

'''Results when removing unknown-word marks (stars)'''

<pre>

</pre>

'''Coverage Test on jya.tests.txt in Bilingual Transducer'''
<pre>

</pre>

[[Category: Japhug]] [[Category: Sp23 StructuralTransfer]]

Japhug and English/Structural Transfer

2023-05-04T19:42:17Z

Ylhamo1: /* Example 1 */

= Pre-Evaluation =

'''Statistics About Input Files'''

<pre>
Number of words in reference: 47
Number of words in test: 33
Number of unknown words (marked with a star) in test: 18
Percentage of unknown words: 54.55 %
</pre>

'''Results when removing unknown-word marks (stars)'''

<pre>
Edit distance: 47
Word error rate (WER): 100.00 %
Number of position-independent correct words: 0
Position-independent word error rate (PER): 100.00 %
</pre>

'''Coverage Test on jya.tests.txt in Bilingual Transducer'''
<pre>
TOP UNKNOWN WORDS:
1 ^ʁnɯtɤrtsɯɣ/*ʁnɯtɤrtsɯɣ$
1 ^ɲɯrganɯ/*ɲɯrganɯ$
1 ^ɲɤmtsɯr/*ɲɤmtsɯr$
1 ^ɯʑo/*ɯʑo$
1 ^ɯtaʁ/*ɯtaʁ$
1 ^ɯjme/*ɯjme$
1 ^ɕɤrɯ/*ɕɤrɯ$
1 ^xuexiao/*xuexiao$
1 ^tʂu/*tʂu$
1 ^pɯ́wɣsɯmtoa/*pɯ́wɣsɯmtoa$
1 ^mɯpɯrɤʑia/*mɯpɯrɤʑia$
1 ^mɯpjɤpenɯ/*mɯpjɤpenɯ$
1 ^mɤpe/*mɤpe$
1 ^kɯkɯra/*kɯkɯra$
1 ^kɤzo/*kɤzo$
1 ^khramba/*khramba$
1 ^aʑo/*aʑo$
1 ^ambro/*ambro$
coverage: 24 / 42 (~0.57142857142857142857)
remaining unknown forms: 18
ambiguity: 54 / 42 (~1.28571428571428571429)
</pre>

= (JYA ‣ ENG) Transfer Evaluation =

We implemented [https://wikis.swarthmore.edu/ling073/Japhug_and_English/ContrastiveGrammars Contrastive Grammar] #1: "For clauses with transitive verbs, in Japhug the object generally precedes the verb (and follows the subject). In English however the object follows the verb."

=== Example 1 ===

'''lɯlu nɯ kɯ βʑɯ ɯɕa tɕi pjɤrga''' outputs '''#that #cat also #like #mouse #meat''' instead of the direct translation #cat that with #mouse #meat also #like.

===== Tagger Output =====
<pre>
^lɯlu<n><ind>$ ^nɯ<det><dem><dist><sg>$ ^kɯ<post>$ ^βʑɯ<n><ind>$ ^ɕa<n><px3sg>$ ^tɕi<adv>$ ^rga<v><tv>$^.<sent>$
</pre>
===== Lex Output =====
<pre>
^lɯlu<n><ind>/cat<n><sg><ind>$ ^nɯ<det><dem><dist><sg>/that<det><dem><sg>$ ^kɯ<post>/with<pr>$ ^βʑɯ<n><ind>/mouse<n><sg><ind>$ ^ɕa<n><px3sg>/meat<n><sg><px3sg>$ ^tɕi<adv>/also<adv>$ ^rga<v><tv>/like<vblex>$^.<sent>/.<sent>$
</pre>
===== Transfer Output =====
<pre>
Applying rule 10 (line 77): ^lɯlu<n><ind>/cat<n><sg><ind>$

Applying rule 12 (line 80): ^default<NP>{^lɯlu<n><ind>/cat<n><sg><ind>$}$

Applying rule 14 (line 83): ^default<dP><CD>{^default<NP>{^lɯlu<n><ind>/cat<n><sg><ind>$}$}$

Applying rule 11 (line 79): ^default<NP>{^lɯlu<n><ind>/cat<n><sg><ind>$}$ ^nɯ<det><dem><dist><sg>/that<det><dem><sg>$

Applying rule 14 (line 83): ^default<dP><CD>{^default<NP>{^lɯlu<n><ind>/cat<n><sg><ind>$}$ ^nɯ<det><dem><dist><sg>/that<det><dem><sg>$}$

Applying rule 13 (line 82): ^default<dP><CD>{^default<NP>{^lɯlu<n><ind>/cat<n><sg><ind>$}$ ^nɯ<det><dem><dist><sg>/that<det><dem><sg>$}$ ^kɯ<post>/with<pr>$

Applying output rule 12 (line 82): default<DP><erg> -> ^default<dP><CD>{^default<NP>{^lɯlu<n><ind>/cat<n><sg><ind>$}$ ^nɯ<det><dem><dist><sg>/that<det><dem><sg>$}$ ^kɯ<post>/with<pr>$

Applying output rule 10 (line 79): default<dP><abs> -> ^default<NP>{^lɯlu<n><ind>/cat<n><sg><ind>$}$ ^nɯ<det><dem><dist><sg>/that<det><dem><sg>$

No rule specified: ^that<det>$

Applying output rule 9 (line 77): default<NP> -> ^lɯlu<n><ind>/cat<n><sg><ind>$

No rule specified: ^cat<n><sg><ind>$

Applying rule 10 (line 77): ^βʑɯ<n><ind>/mouse<n><sg><ind>$

Applying rule 12 (line 80): ^default<NP>{^βʑɯ<n><ind>/mouse<n><sg><ind>$}$

Applying rule 14 (line 83): ^default<dP><CD>{^default<NP>{^βʑɯ<n><ind>/mouse<n><sg><ind>$}$}$

Applying rule 10 (line 77): ^ɕa<n><px3sg>/meat<n><sg><px3sg>$

Applying rule 12 (line 80): ^default<NP>{^ɕa<n><px3sg>/meat<n><sg><px3sg>$}$

Applying rule 14 (line 83): ^default<dP><CD>{^default<NP>{^ɕa<n><px3sg>/meat<n><sg><px3sg>$}$}$

Applying rule 3 (line 70): ^βʑɯ<n><ind>/mouse<n><sg><ind>$ ^ɕa<n><px3sg>/meat<n><sg><px3sg>$

Applying rule 12 (line 80): ^default<NP>{^βʑɯ<n><ind>/mouse<n><sg><ind>$ ^ɕa<n><px3sg>/meat<n><sg><px3sg>$}$

Applying rule 14 (line 83): ^default<dP><CD>{^default<NP>{^βʑɯ<n><ind>/mouse<n><sg><ind>$ ^ɕa<n><px3sg>/meat<n><sg><px3sg>$}$}$

Applying rule 15 (line 88): ^tɕi<adv>/also<adv>$ ^rga<v><tv>/like<vblex>$

Applying rule 17 (line 91): ^default<DP><CD>{^default<dP><CD>{^default<NP>{^ɕa<n><px3sg>/meat<n><sg><px3sg>$}$}$}$ ^default<vP>{^tɕi<adv>/also<adv>$ ^rga<v><tv>/like<vblex>$}$

Applying rule 15 (line 88): ^tɕi<adv>/also<adv>$ ^rga<v><tv>/like<vblex>$

Applying rule 17 (line 91): ^default<DP><CD>{^default<dP><CD>{^default<NP>{^βʑɯ<n><ind>/mouse<n><sg><ind>$ ^ɕa<n><px3sg>/meat<n><sg><px3sg>$}$}$}$ ^default<vP>{^tɕi<adv>/also<adv>$ ^rga<v><tv>/like<vblex>$}$

Applying output rule 16 (line 91): default<S> -> ^default<DP><CD>{^default<dP><CD>{^default<NP>{^βʑɯ<n><ind>/mouse<n><sg><ind>$ ^ɕa<n><px3sg>/meat<n><sg><px3sg>$}$}$}$ ^default<vP>{^tɕi<adv>/also<adv>$ ^rga<v><tv>/like<vblex>$}$

Applying output rule 14 (line 88): default<vP> -> ^tɕi<adv>/also<adv>$ ^rga<v><tv>/like<vblex>$

No rule specified: ^also<adv>$

No rule specified: ^like<vblex>$

Applying output rule 13 (line 83): default<DP><abs> -> ^default<dP><CD>{^default<NP>{^βʑɯ<n><ind>/mouse<n><sg><ind>$ ^ɕa<n><px3sg>/meat<n><sg><px3sg>$}$}$

Applying output rule 11 (line 80): default<dP><abs> -> ^default<NP>{^βʑɯ<n><ind>/mouse<n><sg><ind>$ ^ɕa<n><px3sg>/meat<n><sg><px3sg>$}$

Applying output rule 2 (line 70): default<NP> -> ^βʑɯ<n><ind>/mouse<n><sg><ind>$ ^ɕa<n><px3sg>/meat<n><sg><px3sg>$

No rule specified: ^mouse<n><sg><ind>$

No rule specified: ^meat<n><sg><ind>$

No rule specified: ^.<sent>/.<sent>$
^that<det>$ ^cat<n><sg><ind>$ ^also<adv>$ ^like<vblex>$ ^mouse<n><sg><ind>$ ^meat<n><sg><ind>$^.<sent>$
</pre>
===== JYA-ENG Output =====
<pre>
#that #cat also #like #mouse #meat
</pre>

=== Example 2 ===

'''βzaŋsa tonɯpandʑi''' outputs '''#agree with #friend''' instead of the direct translation #friend #agree with.

===== Tagger Output =====
<pre>
^βzaŋsa<n><ind>$ ^nɯpa<v><tv>$^.<sent>$
</pre>
===== Lex Output =====
<pre>
^βzaŋsa<n><ind>/friend<n><sg><ind>$ ^nɯpa<v><tv>/agree with<vblex>$^.<sent>/.<sent>$
</pre>
===== Transfer Output =====
<pre>
Applying rule 10 (line 77): ^βzaŋsa<n><ind>/friend<n><sg><ind>$

Applying rule 12 (line 80): ^default<NP>{^βzaŋsa<n><ind>/friend<n><sg><ind>$}$

Applying rule 14 (line 83): ^default<dP><CD>{^default<NP>{^βzaŋsa<n><ind>/friend<n><sg><ind>$}$}$

Applying rule 16 (line 89): ^nɯpa<v><tv>/agree with<vblex>$

Applying rule 17 (line 91): ^default<DP><CD>{^default<dP><CD>{^default<NP>{^βzaŋsa<n><ind>/friend<n><sg><ind>$}$}$}$ ^default<vP>{^nɯpa<v><tv>/agree with<vblex>$}$

Applying output rule 16 (line 91): default<VP> -> ^default<DP><CD>{^default<dP><CD>{^default<NP>{^βzaŋsa<n><ind>/friend<n><sg><ind>$}$}$}$ ^default<vP>{^nɯpa<v><tv>/agree with<vblex>$}$

Applying output rule 15 (line 89): default<vP> -> ^nɯpa<v><tv>/agree with<vblex>$

No rule specified: ^agree with<vblex>$

Applying output rule 13 (line 83): default<DP><abs> -> ^default<dP><CD>{^default<NP>{^βzaŋsa<n><ind>/friend<n><sg><ind>$}$}$

Applying output rule 11 (line 80): default<dP><abs> -> ^default<NP>{^βzaŋsa<n><ind>/friend<n><sg><ind>$}$

Applying output rule 9 (line 77): default<NP> -> ^βzaŋsa<n><ind>/friend<n><sg><ind>$

No rule specified: ^friend<n><sg><ind>$

No rule specified: ^.<sent>/.<sent>$
^agree with<vblex>$ ^friend<n><sg><ind>$^.<sent>$
</pre>
===== JYA-ENG Output =====
<pre>
#agree with #friend
</pre>

Our transfer rule successfully switched the object (friend) with the verb phrase (agree with).

= Post-Evaluation =

'''Statistics About Input Files'''

<pre>

</pre>

'''Results when removing unknown-word marks (stars)'''

<pre>

</pre>

'''Coverage Test on jya.tests.txt in Bilingual Transducer'''
<pre>

</pre>

[[Category: Japhug]] [[Category: Sp23 StructuralTransfer]]

Japhug and English/Structural Transfer

2023-05-04T19:40:58Z

Ylhamo1: /* Example 2 */

Japhug and English/Structural Transfer

2023-05-04T19:40:14Z

Ylhamo1: /* Structural Transfer Rule */

Japhug and English/Structural Transfer

2023-05-04T19:34:06Z

Ylhamo1: /* Structural Transfer Rule */

Japhug and English/Structural Transfer

2023-05-04T19:33:48Z

Ylhamo1: /* Structural Transfer Rule */

Japhug and English/Structural Transfer

2023-05-04T19:32:57Z

Ylhamo1: /* Structural Transfer Rule */

Japhug and English/Structural Transfer

2023-05-04T19:17:27Z

Ylhamo1: /* Structural Transfer Rule */

Japhug and English/Structural Transfer

2023-05-04T19:16:48Z

Ylhamo1: /* Structural Transfer Rule */

Japhug and English/Structural Transfer

2023-05-04T19:16:42Z

Ylhamo1:

Japhug and English/Structural Transfer

2023-05-04T17:26:56Z

Ylhamo1: /* Pre-Evaluation */

Japhug and English/Structural Transfer

2023-05-04T17:26:47Z

Ylhamo1: /* Post-Evaluation */

Japhug and English/ContrastiveGrammars

2023-05-03T17:10:19Z

Ylhamo1:

1. For clauses with transitive verbs, in Japhug the object generally precedes the verb (and follows the subject). In English however the object follows the verb.

* {{transferTest|jya|eng|βzaŋsa tonɯpandʑi.|(They) made friends (with each other).}}
: {{transferMorphTest|jya|eng|βzaŋsa{{tag|n}}{{tag|ind}} tonɯpandʑi{{tag|v}}{{tag|du}}|They{{tag|prn}}{{tag|sbj}}{{tag|pl}} made{{tag|vblex}} friends{{tag|n}}{{tag|pl}}}}

(Note: Japhug intransitive verbs require an object but not a subject, unlike in English.)

* {{transferTest|jya|eng|kɯkɯra xuexiao ɲɯrganɯ.|These (the children) like school.}}
: {{transferMorphTest|jya|eng|kɯkɯra{{tag|dem}}{{tag|prox}}{{tag|pl}} xuexiao{{tag|n}}{{tag|ind}} ɲɯrganɯ{{tag|v}}{{tag|sens}}{{tag|pl}}|These{{tag|dem}}{{tag|prox}}{{tag|pl}} like{{tag|vblex}} school{{tag|n}}}}

2. Japhug generally uses postpositions to express relative position (i.e., locative postpositions zɯ, tɕu and ri), whereas English uses prepositions.

* {{transferTest|jya|eng|jonɯɕe tɕe, tʂu tɕu ɲɤmtsɯr.|They went, and on the road they were hungry.}}
: {{transferMorphTest|jya|eng|jonɯɕe{{tag|v}}{{tag|ifr}}{{tag|auto}} tɕe{{tag|lnk}}, tʂu{{tag|n}} tɕu{{tag|post}}{{tag|loc}} ɲɤmtsɯr{{tag|v}}{{tag|ifr}}|They{{tag|prn}}{{tag|sbj}} went{{tag|vblex}}, and{{tag|lnk}} on{{tag|pr}}{{tag|loc}} the{{tag|det}}{{tag|def}} road{{tag|n}} they{{tag|prn}}{{tag|sbj}} were{{tag|aux}}{{tag|past}} hungry{{tag|vblex}}}}

* {{transferTest|jya|eng|ambro ɯjme zɯ kɤzo.|Land on my horse's tail.}}
: {{transferMorphTest|jya|eng|ambro{{tag|n}}{{tag|px1sg}} ɯjme{{tag|n}}{{tag|px3sg}} zɯ{{tag|post}}{{tag|loc}} kɤzo{{tag|v}}{{tag|imp}}|Land{{tag|vblex}} on{{tag|pr}}{{tag|loc}} my{{tag|adv}} horse's{{tag|n}}{{tag|poss}} tail{{tag|n}}}}

3. Japhug expresses negation by a prefix on the verb, where English requires an adverb like "not" (and often an auxiliary verb like "did").

* {{transferTest|jya|eng|aʑo mɯpɯrɤʑia.|I was not present.}}
: {{transferMorphTest|jya|eng|aʑo{{tag|prn}}{{tag|1sg}} mɯpɯrɤʑia{{tag|v}}{{tag|neg}}{{tag|pst}}|I{{tag|prn}}{{tag|1sg}} was{{tag|aux}}{{tag|pst}} not{{tag|adv}}{{tag|neg}} present{{tag|vblex}}}}

* {{transferTest|jya|eng|khramba kɤβzu mɤpe.|Telling lies is bad.}}
: {{transferMorphTest|jya|eng|khramba{{tag|n}} kɤβzu{{tag|v}}{{tag|inf}} mɤpe{{tag|v}}{{tag|neg}}|Telling{{tag|vblex}}{{tag|ipfv}} lies{{tag|n}}{{tag|pl}} is{{tag|v}} bad{{tag|adj}}}}

4. The Japhug causative prefix on verbs would generally require a complementary clause with a verb like "made" on the "original" subject of the verb (i.e., the agent being "caused" to perform the action described by the verb).

* {{transferTest|jya|eng|ɯʑo kɯ nɤʑo pɯ́wɣsɯmtoa.|They caused me to see you.}}
: {{transferMorphTest|jya|eng|ɯʑo{{tag|prn}}{{tag|3sg}} kɯ{{tag|post}}{{tag|erg}} nɤʑo{{tag|prn}}{{tag|2sg}} pɯ́wɣsɯmtoa{{tag|v}}{{tag|ipfv}}{{tag|inv}}{{tag|caus}}{{tag|1sg}}|He{{tag|prn}}{{tag|3sg}} caused{{tag|vblex}}{{tag|pst}} me{{tag|prn}}{{tag|1sg}}{{tag|obj}} to{{tag|aux}} see{{tag|vblex}} you{{tag|prn}}{{tag|2sg}}}}

* {{transferTest|jya|eng|tɤʑɣɤɕɯfka.|Eat to your fill!}}
: {{transferMorphTest|jya|eng|tɤʑɣɤɕɯfka{{tag|v}}{{tag|iv}}{{tag|imp}}{{tag|ref}}{{tag|caus}}|Eat{{tag|vblex}}{{tag|inf}} to{{tag|pr}} your{{tag|det}}{{tag|pos}}{{tag|sp}} fill{{tag|vblex}}{{tag|inf}}}}

5. Japhug verbs can take dual (-ndʑi) and plural (-nɯ) indexation suffixes, that can take the place of second or third person dual/plural pronouns as the object of the verb. E.g., a clause can consist of an intransitive verb alone, with a dual prefix in place of its argument. However it doesn't always do this, it can simply be an agreement with the object(s).

* {{transferTest|jya|eng|ɕɤrɯ nɯ ʁnɯtɤrtsɯɣ toβzundʑi tɕe.|They made two piles from the bones.}}
: {{transferMorphTest|jya|eng|ɕɤrɯ{{tag|n}} nɯ{{tag|dem}} ʁnɯtɤrtsɯɣ{{tag|n}} toβzundʑi{{tag|v}}{{tag|ifr}}{{tag|du}} tɕe{{tag|lnk}}|They{{tag|prn}}{{tag|pl}} made{{tag|vblex}}{{tag|pst}} two{{tag|adj}} piles{{tag|n}}{{tag|pl}} from{{tag|pr}} the{{tag|det}}{{tag|def}} bones{{tag|n}}{{tag|pl}}}}

* {{transferTest|jya|eng|maka ɯtaʁ mɯpjɤpenɯ.|They were not good to him.}}
: {{transferMorphTest|jya|eng|maka{{tag|adv}} ɯtaʁ{{tag|n}}{{tag|px3sg}} mɯpjɤpenɯ{{tag|v}}{{tag|neg}}{{tag|ipfv}}{{tag|ifr}}{{tag|pl}}|They{{tag|prn}}{{tag|pl}} were{{tag|aux}}{{tag|pst}} not{{tag|adv}} good{{tag|adj}} to{{tag|pr}} him{{tag|prn}}{{tag|3sg}}}}

[[Category:Sp23_ContrastiveGrammars ]] [[Category: Japhug]]

Japhug and English/Structural Transfer

2023-05-03T00:32:03Z

Ylhamo1:

Japhug and English/Structural Transfer

2023-05-03T00:31:13Z

Ylhamo1: /* Pre-Evaluation */

Japhug and English/Structural Transfer

2023-05-03T00:24:46Z

Ylhamo1: /* Pre-Evaluation */

Japhug and English/Structural Transfer

2023-05-03T00:14:56Z

Ylhamo1:

Japhug and English/Structural Transfer

2023-05-03T00:12:47Z

Ylhamo1: /* Post-Evaluation */

= Pre-Evaluation =

'''Statistics About Input Files'''

<pre>
Initial WER: 100%
Initial PER: 100%
-------------------------------------------------------
Number of words in reference: 47
Number of words in test: 33
Number of unknown words (marked with a star) in test: 18
Percentage of unknown words: 54.55 %
-------------------------------------------------------
</pre>

= Post-Evaluation =

<pre>
Current WER: %
Current PER: %
-------------------------------------------------------
Number of words in reference:
Number of words in test:
Number of unknown words (marked with a star) in test:
Percentage of unknown words: %
-------------------------------------------------------
</pre>

[[Category: Japhug]] [[Category: Sp23 StructuralTransfer]]

Japhug and English/Structural Transfer

2023-05-03T00:12:38Z

Ylhamo1: /* Post-Evaluation */

= Pre-Evaluation =

'''Statistics About Input Files'''

<pre>
Initial WER: 100%
Initial PER: 100%
-------------------------------------------------------
Number of words in reference: 47
Number of words in test: 33
Number of unknown words (marked with a star) in test: 18
Percentage of unknown words: 54.55 %
-------------------------------------------------------
</pre>

= Post-Evaluation =

<pre>
Current WER: %
Current PER: %
-------------------------------------------------------
Number of words in reference:
Number of words in test:
Number of unknown words (marked with a star) in test:
Percentage of unknown words: %
-------------------------------------------------------
</pre>

Add at least one example sentence for each item you implement. Show the outputs of the following modes for your translation system: tagger, lex, transfer, and the pair itself (abc-xyz).

[[Category: Japhug]] [[Category: Sp23 StructuralTransfer]]

Japhug and English/Structural Transfer

2023-05-03T00:11:58Z

Ylhamo1: /* Post-Evaluation */

Japhug and English/Structural Transfer

2023-05-03T00:11:52Z

Ylhamo1: /* Pre-Evaluation */

= Pre-Evaluation =

'''Statistics About Input Files'''

<pre>
Initial WER: 100%
Initial PER: 100%
-------------------------------------------------------
Number of words in reference: 47
Number of words in test: 33
Number of unknown words (marked with a star) in test: 18
Percentage of unknown words: 54.55 %
-------------------------------------------------------
</pre>

= Post-Evaluation =

<pre>
Current WER: %
Current PER: %
-------------------------------------------------------
Number of words in reference:
Number of words in test:
Number of unknown words (marked with a star) in test:
Percentage of unknown words: %

Results when removing unknown-word marks (stars)
-------------------------------------------------------
</pre>

[[Category: Japhug]] [[Category: Sp23 StructuralTransfer]]

Japhug and English/Structural Transfer

2023-05-03T00:11:47Z

Ylhamo1: /* Pre-Evaluation */

= Pre-Evaluation =

'''Statistics About Input Files'''

<pre>
Initial WER: 100%
Initial PER: 100%
-------------------------------------------------------
Number of words in reference: 47
Number of words in test: 33
Number of unknown words (marked with a star) in test: 18
Percentage of unknown words: 54.55 %

-------------------------------------------------------
</pre>

= Post-Evaluation =

<pre>
Current WER: %
Current PER: %
-------------------------------------------------------
Number of words in reference:
Number of words in test:
Number of unknown words (marked with a star) in test:
Percentage of unknown words: %

Results when removing unknown-word marks (stars)
-------------------------------------------------------
</pre>

[[Category: Japhug]] [[Category: Sp23 StructuralTransfer]]

Japhug and English/Structural Transfer

2023-05-03T00:11:34Z

Ylhamo1: /* Post-Evaluation */

= Pre-Evaluation =

'''Statistics About Input Files'''

<pre>
Initial WER: 100%
Initial PER: 100%
-------------------------------------------------------
Number of words in reference: 47
Number of words in test: 33
Number of unknown words (marked with a star) in test: 18
Percentage of unknown words: 54.55 %

Results when removing unknown-word marks (stars)
-------------------------------------------------------
</pre>

= Post-Evaluation =

<pre>
Current WER: %
Current PER: %
-------------------------------------------------------
Number of words in reference:
Number of words in test:
Number of unknown words (marked with a star) in test:
Percentage of unknown words: %

Results when removing unknown-word marks (stars)
-------------------------------------------------------
</pre>

[[Category: Japhug]] [[Category: Sp23 StructuralTransfer]]

Japhug and English/Structural Transfer

2023-05-03T00:11:00Z

Ylhamo1:

= Pre-Evaluation =

'''Statistics About Input Files'''

<pre>
Initial WER: 100%
Initial PER: 100%
-------------------------------------------------------
Number of words in reference: 47
Number of words in test: 33
Number of unknown words (marked with a star) in test: 18
Percentage of unknown words: 54.55 %

Results when removing unknown-word marks (stars)
-------------------------------------------------------
</pre>

= Post-Evaluation =

<pre>
Initial WER: 100%
Initial PER: 100%
-------------------------------------------------------
Number of words in reference: 47
Number of words in test: 33
Number of unknown words (marked with a star) in test: 18
Percentage of unknown words: 54.55 %

Results when removing unknown-word marks (stars)
-------------------------------------------------------
</pre>

[[Category: Japhug]] [[Category: Sp23 StructuralTransfer]]

Japhug and English/Structural Transfer

2023-05-03T00:07:25Z

Ylhamo1: /* Pre-Evaluation */

Japhug and English/Structural Transfer

2023-05-01T19:02:04Z

Ylhamo1: /* Structural Transfer Pre-Evaluation */

= Pre-Evaluation =

'''Statistics About Input Files'''

<pre>
Initial WER: 100%
Initial PER: 100%
coverage tests on your short sentences corpus
</pre>

[[Category: Japhug]] [[Category: Sp23 StructuralTransfer]]

Japhug and English/Structural Transfer

2023-05-01T19:01:53Z

Ylhamo1:

= Structural Transfer Pre-Evaluation =

'''Statistics About Input Files'''

<pre>
Initial WER: 100%
Initial PER: 100%
coverage tests on your short sentences corpus
</pre>

[[Category: Japhug]] [[Category: Sp23 StructuralTransfer]]

Japhug/Japhug and English

2023-04-28T00:59:05Z

Ylhamo1: /* Jya → Eng evaluation */

==Resources for machine translation between [https://wikis.swarthmore.edu/ling073/Category:Japhug Japhug] and English==

===Developed resources===

[https://github.swarthmore.edu/Ling073-sp23/ling073-jya-eng-corpus Japhug-English corpus]

[https://wikis.swarthmore.edu/ling073/Japhug_and_English/Lexical_selection#jya_.E2.86.92_eng Lexical selection]

==External resources==
[https://github.swarthmore.edu/Ling073-sp23/ling073-jya-eng Apertium language pair for translating between Jiarong and English]

[https://github.swarthmore.edu/Ling073-sp23/ling073-jya Monolingual Japhug transducer]

==Jya → Eng evaluation ==

coverage (number of forms analysed) of Japhug transducer on jya.sentences.txt: 76.98 %

coverage of bilingual transducer (jya-eng.automorf.bin) on the same file: 28.61 %

===10 sentences:===

====#1====
The original sentence:
<pre>
kɯɕɯŋgɯ tɕe, nɤki, lɯlu ci pjɤtu, tɕendɤre βʑɯ ci pjɤtu
</pre>
The intended English translation: A long time ago, there was a cat and a mouse

Output of jya-eng-biltrans:
<pre>
^kɯɕɯŋgɯ<n><ind>/long time ago<cnjadv><ind>$ ^tɕe<cnj>//as for<pr>$^,<cm>/,<cm>$ ^nɤki<dem>/that<det><dem><sg>$^,<cm>/,<cm>$ ^lɯlu<n><ind>/cat<n><sg><ind>$ ^ci<det>/a<det><ind><sg>/one<num><sg>$ ^pjɤtu<cop><other>/be<vbser><other>$^,<cm>/,<cm>$ ^tɕendɤre<cnj>/then<cnjadv>$ ^βʑɯ<n><ind>/mouse<n><sg><ind>$ ^ci<det>/a<det><ind><sg>/one<num><sg>$ ^pjɤtu<cop><other>/be<vbser><other>$^.<sent>/.<sent>$
</pre>

Output of jya-eng:
<pre>
#long time ago , that, #cat a #be, then #mouse a #be
</pre>

====#2====
The original sentence:
<pre>
lɯlu nɯ kɯ nɤkinɯ, βʑɯ ri tundze ɕti
</pre>

The intended English translation: The cat ate the mouse,

Output of jya-eng-biltrans:
<pre>
^lɯlu<n><ind>/cat<n><sg><ind>$ ^nɯ<dem>/that<det><dem><sg>$ ^kɯ<post>/with<pr>$ ^nɤkinɯ<fill>/um<ij>$^,<cm>/,<cm>$ ^βʑɯ<n><ind>/mouse<n><sg><ind>$ ^ri<post>/at<pr>$ ^ndze<v><tv><ipfv>/eat<vblex><ipfv>$ ^ɕti<v><iv>/be<vbser>$^.<sent>/.<sent>$
</pre>

Output of jya-eng:
<pre>
#cat that with um, #mouse at #eat #be
</pre>

====#3====
The original sentence:

<pre>
βʑɯ chondɤre nɤki, kumpɣɤtɕɯ nɯ kɯ βzaŋsa tonɯpandʑi,
</pre>

The intended English translation: The mouse made friends with the sparrow,

Output of jya-eng-biltrans:
<pre>
^βʑɯ<n><ind>/mouse<n><sg><ind>$ ^chondɤre<com>/with<pr>$ ^nɤki<dem>/that<det><dem><sg>$^,<cm>/,<cm>$ ^kumpɣɤtɕɯ<n><ind>/sparrow<n><sg><ind>$ ^nɯ<dem>/that<det><dem><sg>$ ^kɯ<post>/with<pr>$ ^βzaŋsa<n><ind>/friend<n><sg><ind>$ ^tonɯpa<v><tv><du>/made<vblex><pp><du>$^,<cm>/,<cm>$^.<sent>/.<sent>$
</pre>

Output of jya-eng:
<pre>
#mouse with that, #sparrow that with #friend #made,
</pre>

====#4====
The original sentence:
<pre>
tɕe βzaŋsa tonɯpandʑi tɕe, wuma pjɤkɤmɯmindʑici
</pre>

The intended English translation: The two of them become friends and got along well

Output of jya-eng-biltrans:
<pre>
^tɕe<cnj>//as for<pr>$ ^βzaŋsa<n><ind>/friend<n><sg><ind>$ ^tonɯpa<v><tv><du>/made<vblex><pp><du>$ ^tɕe<cnj>//as for<pr>$^,<cm>/,<cm>$ ^wuma<adv>/very<adv>$ ^ɤmɯmi<v><iv><pii><du>/get along well<vblex><pii><du>$^.<sent>/.<sent>$</pre>
Output of jya-eng:
<pre>
#friend #made , very #get along well
</pre>

====#5====
The original sentence:
<pre>
maka cici ŋotɕu jɤarɯrindʑi ʑo tɯtɯrca ntsɯ juɕendʑi pjɤŋu
</pre>
The intended English translation: they always got together

Output of jya-eng-biltrans:
<pre>
^maka<adv>/at all<adv>$ ^cici<adv>/sometimes<adv>$ ^ŋotɕu<prn>/wherever<adv>$ ^*jɤarɯrindʑi/*jɤarɯrindʑi$ ^*ʑo/*ʑo$ ^*tɯtɯrca/*tɯtɯrca$ ^ntsɯ<adv>/always<adv>$ ^*juɕendʑi/*juɕendʑi$ ^ŋu<v><iv><pii>/be<vbser><pii>$^.<sent>/.<sent>$
</pre>
Output of jya-eng:
<pre>
at all sometimes wherever #each together always #go #be
</pre>

====#6====
The original sentence:
<pre>
kɤndza ci tu nɤ pjɯnɯkrondʑi
</pre>
The intended English translation: There was food to eat, they shared,

Output of jya-eng-biltrans:
<pre>
^kɤndza<n><ind>/food<n><sg><ind>$ ^ci<det>/a<det><ind><sg>/one<num><sg>$ ^tu<v><iv>/be<vbser>/exist<vblex>$ ^*nɤ/*nɤ$ ^*pjɯnɯkrondʑi/*pjɯnɯkrondʑi$^.<sent>/.<sent>$
</pre>
Output of jya-eng:
<pre>
#food a #be at #share
</pre>

====#7====
The original sentence:
<pre>
nɯ mɤʑɯ kɯmtɕhɯ kɯfse tɤtu nɤ, tɯɣrɤz ɲɯnɤɣrondʑi nɯ ra pjɤŋgrɤl
</pre>

The intended English translation: Also, when there was something to play with, they played together

Output of jya-eng-biltrans:
<pre>
^nɯ<dem>/that<det><dem><sg>$ ^mɤʑɯ<adv>/again<adv>$ ^kɯmtɕhɯ<n><ind>/toy<n><sg><ind>$ ^fse<v><tv><prc><sbj><ind>/resemble<vblex><prc><sbj><ind>$ ^tu<v><iv><aor>/be<vbser><aor>/exist<vblex><aor>$ ^nɤ<post>/at<pr>$^,<cm>/,<cm>$ ^tɯɣrɤz<adv>/together<adv>$ ^nɤɣro<v><tv><ipfv><du>/play<vblex><inf><ipfv><du>$ ^nɯ<dem>/that<det><dem><sg>$ ^ra<v><iv>/should<vbmod>$ ^ŋgrɤl<v><iv><pii>/usually like this<iv><pii>$^.<sent>/.<sent>$
</pre>

Output of jya-eng:
<pre>
that again #toy #resemble #be at, together #play that #should #usually like this
</pre>

====#8====
The original sentence:
<pre>
tɕhi kɤcha tukɤpjɤl kowa ntsɯ tuβzundʑi pjɤŋu tɕe
</pre>

The intended English translation: They were always trying to think of ways to evade that cat

Output of jya-eng-biltrans:
<pre>
^tɕhi<prn>/what<prn>$ ^cha<v><iv><prc><obj><ind>/able<adj><prc><obj><ind>/can<vbmod><prc><obj><ind>$ ^pjɤl<v><tv><inf><ipfv>/evade<vblex><inf><ipfv>$ ^kowa<n><ind>/method<n><sg><ind>$ ^ntsɯ<adv>/always<adv>$ ^βzu<v><tv><ipfv><du>/make<vblex><ipfv><du>$ ^ŋu<v><iv><pii>/be<vbser><pii>$ ^tɕe<cnj>//as for<pr>$^.<sent>/.<sent>$
</pre>

Output of jya-eng:
<pre>
#what #able #evade #method always #make #be
</pre>

====#9====
The original sentence:
<pre>
lɯlu nɯ kɯ βʑɯ ɯɕa tɕi pjɤrga, pɣɤtɕɯ ɯɕa tɕi pjɤrga ɕti tɕe.
</pre>

The intended English translation: The cat likes eating rat meat, and also likes sparrow meat.

Output of jya-eng-biltrans:
<pre>
^lɯlu<n><ind>/cat<n><sg><ind>$ ^nɯ<dem>/that<det><dem><sg>$ ^kɯ<post>/with<pr>$ ^βʑɯ<n><ind>/mouse<n><sg><ind>$ ^ɕa<n><px3sg>/meat<n><sg><px3sg>$ ^tɕi<adv>/also<adv>$ ^rga<v><iv><pii>/like<vblex><pii>$^,<cm>/,<cm>$ ^pɣɤtɕɯ<n><ind>/bird<n><sg><ind>$ ^ɕa<n><px3sg>/meat<n><sg><px3sg>$ ^tɕi<adv>/also<adv>$ ^rga<v><iv><pii>/like<vblex><pii>$ ^ɕti<v><iv>/be<vbser>$ ^tɕe<cnj>//as for<pr>$^.<sent>/.<sent>$^.<sent>/.<sent>$
</pre>

Output of jya-eng:
<pre>
#cat that with #mouse #meat also #like, #bird #meat also #like #be .
</pre>

====#10====
The original sentence:
<pre>
tɕe nɯ maʁ nɤ tɕe, βʑɯ nɯ kɯ wuma kɤrɤfsoʁ pjɤcha tɕe
</pre>

The intended English translation: since then, that mouse was very good at accumulating food

Output of jya-eng-biltrans:
<pre>
^tɕe<cnj>//as for<pr>$ ^nɯ maʁ nɤ<cnj>/or<cnjcoo>$ ^tɕe<cnj>//as for<pr>$^,<cm>/,<cm>$ ^βʑɯ<n><ind>/mouse<n><sg><ind>$ ^nɯ<dem>/that<det><dem><sg>$ ^kɯ<post>/with<pr>$ ^wuma<adv>/very<adv>$ ^rɤfsoʁ<v><iv><prc><obj><ind>/forage<vblex><prc><obj><ind>$ ^cha<v><iv><pii>/able<adj><pii>/can<vbmod><pii>$ ^tɕe<cnj>//as for<pr>$^.<sent>/.<sent>$
</pre>

Output of jya-eng:
<pre>
or , #mouse that with very #forage #able
</pre>

[[Category:Sp23_TranslationPairs ]] [[Category: Japhug]]

Japhug and English/Lexical selection

2023-04-28T00:46:03Z

Ylhamo1: /* jya → eng */

==jya → eng ==

at least two cases of a one-to-many mapping (2 sentences minimum for each word):

# There are three locative postpositions in Japhug, zɯ, tɕu and ri. All three can be used to express location ("at", "on", "in"), motion into ("into"), motion towards ("to"), or motion away from a place ("from"), irrespective of semantic details like relative location (on top, below, inside, etc.). Thus all three might be ambiguously translated to any of a number of English prepositions.

# The standard third person pronouns in Japhug do not distinguish for animacy or semantic gender. For one example, in English, the third person singular pronoun is "it" for inanimate (or nonhuman) referents, but "he"/"she"/"they" and their conjugations "him"/"her"/"them" for animate referents depending on the perceived semantic gender of the referent. In Japhug, "ɯʑo" (in the Kamnyu dialect) or "mi" (Tatshi dialect) is the third person singular pronoun always.

Example sentence: tɕeri '''ɯʑo''' ndɤre, qajdo cʰo ra kɯ ndɤ tú-wɣ-ndza ɕti

but 3sg advers crow comit pl erg advers ipfv-inv-eat be.aff:fact

This sentence could be translated as "But it is eaten by crows and other [animals]", or as "But she is eaten by crows and other [animals]", etc.

# The particle tɕe serves as the optional topic marker of a sentence. Generally, when it is at the beginning of a sentence, it can be translated as "as for ...", while it doesn't have corresponding translation in other places.

# kɤntɕhaʁ → street; village
##kɤntɕhaʁ rɤʑi-a (I'm on the street)
##a-jɤ-tɯ-ɣɯt tɕe, aʑo cʰo [...] tɤɕime nɯ kɯ nɯnɯ kɤntɕʰaʁ ɣɯ ɯ-pɕi nɯtɕu ku-ta-nɤjo. (When you bring [the bird], the princess and I will be waiting for you outside of the town.)
# kha → house; original place
## kɯ-rlaʁ kʰa (An abandoned house)
##
# '''khe → stupid; cloudy day '''
##'''kɯ-khe ci ɲɯ-ŋu (He is a fool)'''
##'''tɯ-mɯ ɲɯ-khe (The sky is cloudy)'''

'''Generalisation for how to decide which translation is right: if there is tɯ-mɯ (‘sky, weather’) before khe, set translation to 'cloudy''''

==eng → jya==

# The second person pronoun "you" in English does not distinguish singular, dual, and plural referents. In Japhug (Kamnyu dialect), the 2p singular pronoun is nɤʑo or nɤj; the 2p dual is ndʑiʑo; and the 2p plural is nɯʑo, nɯʑora, or nɯʑɤra.

To select these, one generalization we came up with is that "you" with a dual or plural referent in English is often followed by another noun that carries that meaning. For example, the phrases "you two" or "you both" unambiguously refer to a dual referent. "You all", "you guys", or "you" followed by a plural noun (e.g "you people", "you musicians", etc.) unambiguously refer to a plural referent.

Example unambiguous sentences:

- "I enjoy spending time with '''you all'''."

- "I think that '''you two''' need to stop causing trouble."

# The English word "food" has two possible Japhug translation: kɤndza and tɯjpu, where kɤndza refers to processed food that are ready to eat and tɯjpu refers to food that are agricultural products not ready to eat.

[[Category:Sp23_LexicalSelection]][[Category:Japhug]][[Category:English]]

Japhug and English/Lexical selection

2023-04-28T00:15:21Z

Ylhamo1: /* jya → eng */

==jya → eng ==

at least two cases of a one-to-many mapping (2 sentences minimum for each word):

# There are three locative postpositions in Japhug, zɯ, tɕu and ri. All three can be used to express location ("at", "on", "in"), motion into ("into"), motion towards ("to"), or motion away from a place ("from"), irrespective of semantic details like relative location (on top, below, inside, etc.). Thus all three might be ambiguously translated to any of a number of English prepositions.

# The standard third person pronouns in Japhug do not distinguish for animacy or semantic gender. For one example, in English, the third person singular pronoun is "it" for inanimate (or nonhuman) referents, but "he"/"she"/"they" and their conjugations "him"/"her"/"them" for animate referents depending on the perceived semantic gender of the referent. In Japhug, "ɯʑo" (in the Kamnyu dialect) or "mi" (Tatshi dialect) is the third person singular pronoun always.

Example sentence: tɕeri '''ɯʑo''' ndɤre, qajdo cʰo ra kɯ ndɤ tú-wɣ-ndza ɕti

but 3sg advers crow comit pl erg advers ipfv-inv-eat be.aff:fact

This sentence could be translated as "But it is eaten by crows and other [animals]", or as "But she is eaten by crows and other [animals]", etc.

# The particle tɕe serves as the optional topic marker of a sentence. Generally, when it is at the beginning of a sentence, it can be translated as "as for ...", while it doesn't have corresponding translation in other places.

# kɤntɕhaʁ → street; village
##kɤntɕhaʁ rɤʑi-a (I'm on the street)
##a-jɤ-tɯ-ɣɯt tɕe, aʑo cʰo [...] tɤɕime nɯ kɯ nɯnɯ kɤntɕʰaʁ ɣɯ ɯ-pɕi nɯtɕu ku-ta-nɤjo. (When you bring [the bird], the princess and I will be waiting for you outside of the town.)
# kha → house; original place
## kɯ-rlaʁ kʰa (An abandoned house)
##
# khe → stupid; cloudy day
##kɯ-khe ci ɲɯ-ŋu (He is a fool)
##tɯ-mɯ ɲɯ-khe (The sky is cloudy)

Generalisation for how to decide which translation is right: if there is tɯ-mɯ (‘sky, weather’) before khe, set translation to 'cloudy'

==eng → jya==

# The second person pronoun "you" in English does not distinguish singular, dual, and plural referents. In Japhug (Kamnyu dialect), the 2p singular pronoun is nɤʑo or nɤj; the 2p dual is ndʑiʑo; and the 2p plural is nɯʑo, nɯʑora, or nɯʑɤra.

To select these, one generalization we came up with is that "you" with a dual or plural referent in English is often followed by another noun that carries that meaning. For example, the phrases "you two" or "you both" unambiguously refer to a dual referent. "You all", "you guys", or "you" followed by a plural noun (e.g "you people", "you musicians", etc.) unambiguously refer to a plural referent.

Example unambiguous sentences:

- "I enjoy spending time with '''you all'''."

- "I think that '''you two''' need to stop causing trouble."

# The English word "food" has two possible Japhug translation: kɤndza and tɯjpu, where kɤndza refers to processed food that are ready to eat and tɯjpu refers to food that are agricultural products not ready to eat.

[[Category:Sp23_LexicalSelection]][[Category:Japhug]][[Category:English]]

Japhug and English/Lexical selection

2023-04-28T00:14:24Z

Ylhamo1: /* jya → eng */

==jya → eng ==

at least two cases of a one-to-many mapping (2 sentences minimum for each word):

# There are three locative postpositions in Japhug, zɯ, tɕu and ri. All three can be used to express location ("at", "on", "in"), motion into ("into"), motion towards ("to"), or motion away from a place ("from"), irrespective of semantic details like relative location (on top, below, inside, etc.). Thus all three might be ambiguously translated to any of a number of English prepositions.

# The standard third person pronouns in Japhug do not distinguish for animacy or semantic gender. For one example, in English, the third person singular pronoun is "it" for inanimate (or nonhuman) referents, but "he"/"she"/"they" and their conjugations "him"/"her"/"them" for animate referents depending on the perceived semantic gender of the referent. In Japhug, "ɯʑo" (in the Kamnyu dialect) or "mi" (Tatshi dialect) is the third person singular pronoun always.

Example sentence: tɕeri '''ɯʑo''' ndɤre, qajdo cʰo ra kɯ ndɤ tú-wɣ-ndza ɕti

but 3sg advers crow comit pl erg advers ipfv-inv-eat be.aff:fact

This sentence could be translated as "But it is eaten by crows and other [animals]", or as "But she is eaten by crows and other [animals]", etc.

# The particle tɕe serves as the optional topic marker of a sentence. Generally, when it is at the beginning of a sentence, it can be translated as "as for ...", while it doesn't have corresponding translation in other places.

# kɤntɕhaʁ → street; village
##kɤntɕhaʁ rɤʑi-a (I'm on the street)
##a-jɤ-tɯ-ɣɯt tɕe, aʑo cʰo [...] tɤɕime nɯ kɯ nɯnɯ kɤntɕʰaʁ ɣɯ ɯ-pɕi nɯtɕu ku-ta-nɤjo. (When you bring [the bird], the princess and I will be waiting for you outside of the town.)
# kha → house; original place
## kɯ-rlaʁ kʰa (An abandoned house)
##
# khe → stupid; cloudy day
##kɯ-khe ci ɲɯ-ŋu (He is a fool)
##tɯ-mɯ ɲɯ-khe (The sky is cloudy)

How to decide which translation is right: if there is tɯ-mɯ (‘sky, weather’) before khe, set translation to 'cloudy'

==eng → jya==

# The second person pronoun "you" in English does not distinguish singular, dual, and plural referents. In Japhug (Kamnyu dialect), the 2p singular pronoun is nɤʑo or nɤj; the 2p dual is ndʑiʑo; and the 2p plural is nɯʑo, nɯʑora, or nɯʑɤra.

To select these, one generalization we came up with is that "you" with a dual or plural referent in English is often followed by another noun that carries that meaning. For example, the phrases "you two" or "you both" unambiguously refer to a dual referent. "You all", "you guys", or "you" followed by a plural noun (e.g "you people", "you musicians", etc.) unambiguously refer to a plural referent.

Example unambiguous sentences:

- "I enjoy spending time with '''you all'''."

- "I think that '''you two''' need to stop causing trouble."

# The English word "food" has two possible Japhug translation: kɤndza and tɯjpu, where kɤndza refers to processed food that are ready to eat and tɯjpu refers to food that are agricultural products not ready to eat.

[[Category:Sp23_LexicalSelection]][[Category:Japhug]][[Category:English]]

Japhug and English/Lexical selection

2023-04-28T00:14:06Z

Ylhamo1: /* jya → eng */

==jya → eng ==

at least two cases of a one-to-many mapping (2 sentences minimum for each word):

# There are three locative postpositions in Japhug, zɯ, tɕu and ri. All three can be used to express location ("at", "on", "in"), motion into ("into"), motion towards ("to"), or motion away from a place ("from"), irrespective of semantic details like relative location (on top, below, inside, etc.). Thus all three might be ambiguously translated to any of a number of English prepositions.

# The standard third person pronouns in Japhug do not distinguish for animacy or semantic gender. For one example, in English, the third person singular pronoun is "it" for inanimate (or nonhuman) referents, but "he"/"she"/"they" and their conjugations "him"/"her"/"them" for animate referents depending on the perceived semantic gender of the referent. In Japhug, "ɯʑo" (in the Kamnyu dialect) or "mi" (Tatshi dialect) is the third person singular pronoun always.

Example sentence: tɕeri '''ɯʑo''' ndɤre, qajdo cʰo ra kɯ ndɤ tú-wɣ-ndza ɕti

but 3sg advers crow comit pl erg advers ipfv-inv-eat be.aff:fact

This sentence could be translated as "But it is eaten by crows and other [animals]", or as "But she is eaten by crows and other [animals]", etc.

# The particle tɕe serves as the optional topic marker of a sentence. Generally, when it is at the beginning of a sentence, it can be translated as "as for ...", while it doesn't have corresponding translation in other places.

# kɤntɕhaʁ → street; village
##kɤntɕhaʁ rɤʑi-a (I'm on the street)
##a-jɤ-tɯ-ɣɯt tɕe, aʑo cʰo [...] tɤɕime nɯ kɯ nɯnɯ kɤntɕʰaʁ ɣɯ ɯ-pɕi nɯtɕu ku-ta-nɤjo. (When you bring [the bird], the princess and I will be waiting for you outside of the town.)
# kha → house; original place
## kɯ-rlaʁ kʰa (An abandoned house)
##
# khe → stupid; cloudy day
##kɯ-khe ci ɲɯ-ŋu (He is a fool)
##tɯ-mɯ ɲɯ-khe (The sky is cloudy)

How to decide which translation is right: if there is tɯ-mɯ (‘sky, weather’), set translation to 'cloudy'

==eng → jya==

# The second person pronoun "you" in English does not distinguish singular, dual, and plural referents. In Japhug (Kamnyu dialect), the 2p singular pronoun is nɤʑo or nɤj; the 2p dual is ndʑiʑo; and the 2p plural is nɯʑo, nɯʑora, or nɯʑɤra.

To select these, one generalization we came up with is that "you" with a dual or plural referent in English is often followed by another noun that carries that meaning. For example, the phrases "you two" or "you both" unambiguously refer to a dual referent. "You all", "you guys", or "you" followed by a plural noun (e.g "you people", "you musicians", etc.) unambiguously refer to a plural referent.

Example unambiguous sentences:

- "I enjoy spending time with '''you all'''."

- "I think that '''you two''' need to stop causing trouble."

# The English word "food" has two possible Japhug translation: kɤndza and tɯjpu, where kɤndza refers to processed food that are ready to eat and tɯjpu refers to food that are agricultural products not ready to eat.

[[Category:Sp23_LexicalSelection]][[Category:Japhug]][[Category:English]]

Japhug and English/Lexical selection

2023-04-27T23:54:37Z

Ylhamo1: /* jya → eng */

==jya → eng ==

at least two cases of a one-to-many mapping (2 sentences minimum for each word):

# There are three locative postpositions in Japhug, zɯ, tɕu and ri. All three can be used to express location ("at", "on", "in"), motion into ("into"), motion towards ("to"), or motion away from a place ("from"), irrespective of semantic details like relative location (on top, below, inside, etc.). Thus all three might be ambiguously translated to any of a number of English prepositions.

# The standard third person pronouns in Japhug do not distinguish for animacy or semantic gender. For one example, in English, the third person singular pronoun is "it" for inanimate (or nonhuman) referents, but "he"/"she"/"they" and their conjugations "him"/"her"/"them" for animate referents depending on the perceived semantic gender of the referent. In Japhug, "ɯʑo" (in the Kamnyu dialect) or "mi" (Tatshi dialect) is the third person singular pronoun always.

Example sentence: tɕeri '''ɯʑo''' ndɤre, qajdo cʰo ra kɯ ndɤ tú-wɣ-ndza ɕti

but 3sg advers crow comit pl erg advers ipfv-inv-eat be.aff:fact

This sentence could be translated as "But it is eaten by crows and other [animals]", or as "But she is eaten by crows and other [animals]", etc.

# The particle tɕe serves as the optional topic marker of a sentence. Generally, when it is at the beginning of a sentence, it can be translated as "as for ...", while it doesn't have corresponding translation in other places.

# kɤntɕhaʁ → street; village
##kɤntɕhaʁ rɤʑi-a (I'm on the street)
##a-jɤ-tɯ-ɣɯt tɕe, aʑo cʰo [...] tɤɕime nɯ kɯ nɯnɯ kɤntɕʰaʁ ɣɯ ɯ-pɕi nɯtɕu ku-ta-nɤjo. (When you bring [the bird], the princess and I will be waiting for you outside of the town.)
# kha → house; original place
## kɯ-rlaʁ kʰa (An abandoned house)
##
# khe → stupid; cloudy day
##kɯ-khe ci ɲɯ-ŋu (He is a fool)
##tɯ-mɯ ɲɯ-khe (The sky is cloudy)

how to decide which translation is right: if there is tɯ-mɯ (‘sky, weather’), set translation to 'cloudy'

==eng → jya==

# The second person pronoun "you" in English does not distinguish singular, dual, and plural referents. In Japhug (Kamnyu dialect), the 2p singular pronoun is nɤʑo or nɤj; the 2p dual is ndʑiʑo; and the 2p plural is nɯʑo, nɯʑora, or nɯʑɤra.

To select these, one generalization we came up with is that "you" with a dual or plural referent in English is often followed by another noun that carries that meaning. For example, the phrases "you two" or "you both" unambiguously refer to a dual referent. "You all", "you guys", or "you" followed by a plural noun (e.g "you people", "you musicians", etc.) unambiguously refer to a plural referent.

Example unambiguous sentences:

- "I enjoy spending time with '''you all'''."

- "I think that '''you two''' need to stop causing trouble."

# The English word "food" has two possible Japhug translation: kɤndza and tɯjpu, where kɤndza refers to processed food that are ready to eat and tɯjpu refers to food that are agricultural products not ready to eat.

[[Category:Sp23_LexicalSelection]][[Category:Japhug]][[Category:English]]