Urum and English/Structural Transfer

From LING073
Revision as of 17:50, 29 April 2023 by Scasada1 (talk | contribs) (→‎Transfer Output:)

Jump to: navigation, search

External resources

Transducer Links

Language Pair Repository

Structural Transfer Pre-Evaluation

Statistics About Input Files

(ling073-uum-eng-corpus/eng.sentences.txt & ling073-uum-eng/pre-eval_uum-eng.tests.txt)
Number of words in reference: 231
Number of words in test: 182
Number of unknown words (marked with a star) in test: 76
Percentage of unknown words: 41.76 %


Results when removing unknown-word marks (stars)

Edit distance: 231
Word error rate (WER): 100.00 %
Number of position-independent correct words: 7
Position-independent word error rate (PER): 96.97 %

Coverage Tests

TOP UNKNOWN WORDS:
     3 ^да/*да$
     2 ^тʼетти/*тʼетти$
     2 ^тʼетирдилер/*тʼетирдилер$
     2 ^доғуштан/*доғуштан$
     1 ^ӧстӱ/*ӧстӱ$
     1 ^җеннет/*җеннет$
     1 ^эң/*эң$
     1 ^эништилер/*эништилер$
     1 ^энди/*энди$
     1 ^ышхын/*ышхын$
     1 ^ышихындан/*ышихындан$
     1 ^чобанлара/*чобанлара$
     1 ^чобанлар/*чобанлар$
     1 ^чобаллара/*чобаллара$
     1 ^чине/*чине$
     1 ^хырды/*хырды$
     1 ^хутхарды/*хутхарды$
     1 ^хорхундулар/*хорхундулар$
     1 ^хонуштулар/*хонуштулар$
     1 ^хонду/*хонду$
coverage: 130 / 206 (~0.63106796116504854369)
remaining unknown forms: 76

(UUM ‣ ENG) Transfer Evaluation

Example 1 (Verb Pronoun Marking)

  • (uum) алйым → (eng) I find
    (uum) ал<v><tv><pres><p1><sg> → (eng) I<prn><subj><p1><m><sg>find<vblex><pres>
Tagger Output:
^ал<v><tv><pres><p1><sg>$^.<sent>$
Lex Output:
^ал<v><tv><pres><p1><sg>/take<vblex><tv><pres><p1><sg>/stay<vblex><tv><pres><p1><sg>$^.<sent>/.<sent>$
Transfer Output:
 Applying rule 71 (line 521): ^ал<v><tv><pres><p1><sg>/take<vblex><tv><pres><p1><sg>$
 Applying rule 62 (line 463): ^ал<vP><tv><pres><fin><p1><sg><aff><QD><NFD><NOaux>{^ал<v><tv><pres><p1><sg>/take<vblex><tv><pres><p1><sg>$}$
 Applying rule 82 (line 568): ^ал<VP><fin><tv><pres><p1><sg><aff><QD><NFD><NOaux><NOitg><NObarjoq>{^ал<vP><tv><pres><fin><p1><sg><aff><QD><NFD><NOaux>{^ал<v><tv><pres><p1><sg>/take<vblex><tv><pres><p1><sg>$}$}$
 Applying rule 86 (line 573): ^default<S>{^ал<VP><fin><tv><pres><p1><sg><aff><QD><NFD><NOaux><NOitg><NObarjoq>{^ал<vP><tv><pres><fin><p1><sg><aff><QD><NFD><NOaux>{^ал<v><tv><pres><p1><sg>/take<vblex><tv><pres><p1><sg>$}$}$}$^.<sent>/.<sent>$
 Applying output rule 85 (line 573): default</S> -> ^default<S>{^ал<VP><fin><tv><pres><p1><sg><aff><QD><NFD><NOaux><NOitg><NObarjoq>{^ал<vP><tv><pres><fin><p1><sg><aff><QD><NFD><NOaux>{^ал<v><tv><pres><p1><sg>/take<vblex><tv><pres><p1><sg>$}$}$}$^.<sent>/.<sent>$
 Applying output rule 81 (line 568): default<S> -> ^ал<VP><fin><tv><pres><p1><sg><aff><QD><NFD><NOaux><NOitg><NObarjoq>{^ал<vP><tv><pres><fin><p1><sg><aff><QD><NFD><NOaux>{^ал<v><tv><pres><p1><sg>/take<vblex><tv><pres><p1><sg>$}$}$
 No rule specified: ^prpers<prn><subj><p1><m><sg>$
 Applying output rule 61 (line 463): ал<VP><fin><tv><pres><p1><sg><aff><NOqst><noNF><do><NOitg><NObarjoq> -> ^ал<vP><tv><pres><fin><p1><sg><aff><QD><NFD><NOaux>{^ал<v><tv><pres><p1><sg>/take<vblex><tv><pres><p1><sg>$}$
 Applying output rule 70 (line 521): ал<vP><tv><pres><fin><p1><sg><aff><NOqst><noNF><do> -> ^ал<v><tv><pres><p1><sg>/take<vblex><tv><pres><p1><sg>$
 No rule specified: ^take<vblex><pres>$
 No rule specified: ^.<sent>$
^prpers<prn><subj><p1><m><sg>$ ^take<vblex><pres>$ ^.<sent>$
UUM-ENG Output:
I take

Example 2 (Verb Past-Tense)

  • (uum) булду → (eng) he found
    (uum) бул<v><tv><past><p3><sg> → (eng) he<prn><p3><m><sg>find<vblex><past>
Tagger Output:
^бул<v><tv><past><p3><sg>$^.<sent>$
Lex Output:
^бул<v><tv><past><p3><sg>/find<vblex><tv><past><p3><sg>$^.<sent>/.<sent>$
Transfer Output:
 Applying rule 71 (line 521): ^бул<v><tv><past><p3><sg>/find<vblex><tv><past><p3><sg>$
 Applying rule 62 (line 463): ^бул<vP><tv><past><fin><p3><sg><aff><QD><NFD><NOaux>{^бул<v><tv><past><p3><sg>/find<vblex><tv><past><p3><sg>$}$
 Applying rule 82 (line 568): ^бул<VP><fin><tv><past><p3><sg><aff><QD><NFD><NOaux><NOitg><NObarjoq>{^бул<vP><tv><past><fin><p3><sg><aff><QD><NFD><NOaux>{^бул<v><tv><past><p3><sg>/find<vblex><tv><past><p3><sg>$}$}$
 Applying rule 86 (line 573): ^default<S>{^бул<VP><fin><tv><past><p3><sg><aff><QD><NFD><NOaux><NOitg><NObarjoq>{^бул<vP><tv><past><fin><p3><sg><aff><QD><NFD><NOaux>{^бул<v><tv><past><p3><sg>/find<vblex><tv><past><p3><sg>$}$}$}$^.<sent>/.<sent>$
 Applying output rule 85 (line 573): default<S> -> ^default<S>{^бул<VP><fin><tv><past><p3><sg><aff><QD><NFD><NOaux><NOitg><NObarjoq>{^бул<vP><tv><past><fin><p3><sg><aff><QD><NFD><NOaux>{^бул<v><tv><past><p3><sg>/find<vblex><tv><past><p3><sg>$}$}$}$^.<sent>/.<sent>$
 Applying output rule 81 (line 568): default<S> -> ^бул<VP><fin><tv><past><p3><sg><aff><QD><NFD><NOaux><NOitg><NObarjoq>{^бул<vP><tv><past><fin><p3><sg><aff><QD><NFD><NOaux>{^бул<v><tv><past><p3><sg>/find<vblex><tv><past><p3><sg>$}$}$
 No rule specified: ^prpers<prn><subj><p3><m><sg>$
 Applying output rule 61 (line 463): бул<VP><fin><tv><past><p3><sg><aff><NOqst><noNF><do><NOitg><NObarjoq> -> ^бул<vP><tv><past><fin><p3><sg><aff><QD><NFD><NOaux>{^бул<v><tv><past><p3><sg>/find<vblex><tv><past><p3><sg>$}$
 Applying output rule 70 (line 521): бул<vP><tv><past><fin><p3><sg><aff><NOqst><noNF><do> -> ^бул<v><tv><past><p3><sg>/find<vblex><tv><past><p3><sg>$
 No rule specified: ^find<vblex><past>$
 No rule specified: ^.<sent>$
^prpers<prn><subj><p3><m><sg>$ ^find<vblex><past>$ ^.<sent>$
UUM-ENG Output:
he found

Example 3 (Verb Negativity)

  • (uum) булмады → (eng) he did not find
    (uum) бул<v><tv><neg><past><p3><sg> → (eng) he<prn><p3><m><sg>did<vblex><past>not<adv> find<vblex><pres>
Tagger Output:
^бул<v><tv><neg><past><p3><sg>$^.<sent>$
Lex Output:
^бул<v><tv><neg><past><p3><sg>/find<vblex><tv><neg><past><p3><sg>$^.<sent>/.<sent>$
Transfer Output:
 Applying rule 72 (line 536): ^бул<v><tv><neg><past><p3><sg>/find<vblex><tv><neg><past><p3><sg>$
 Applying rule 62 (line 463): ^бул<vP><tv><past><fin><p3><sg><neg><QD><NFD><NOaux>{^бул<v><tv><neg><past><p3><sg>/find<vblex><tv><neg><past><p3><sg>$}$
 Applying rule 82 (line 568): ^бул<VP><fin><tv><past><p3><sg><neg><QD><NFD><NOaux><NOitg><NObarjoq>{^бул<vP><tv><past><fin><p3><sg><neg><QD><NFD><NOaux>{^бул<v><tv><neg><past><p3><sg>/find<vblex><tv><neg><past><p3><sg>$}$}$
 Applying rule 86 (line 573): ^default<S>{^бул<VP><fin><tv><past><p3><sg><neg><QD><NFD><NOaux><NOitg><NObarjoq>{^бул<vP><tv><past><fin><p3><sg><neg><QD><NFD><NOaux>{^бул<v><tv><neg><past><p3><sg>/find<vblex><tv><neg><past><p3><sg>$}$}$}$^.<sent>/.<sent>$
 Applying output rule 85 (line 573): default<S> -> ^default<S>{^бул<VP><fin><tv><past><p3><sg><neg><QD><NFD><NOaux><NOitg><NObarjoq>{^бул<vP><tv><past><fin><p3><sg><neg><QD><NFD><NOaux>{^бул<v><tv><neg><past><p3><sg>/find<vblex><tv><neg><past><p3><sg>$}$}$}$^.<sent>/.<sent>$
 Applying output rule 81 (line 568): default<S> -> ^бул<VP><fin><tv><past><p3><sg><neg><QD><NFD><NOaux><NOitg><NObarjoq>{^бул<vP><tv><past><fin><p3><sg><neg><QD><NFD><NOaux>{^бул<v><tv><neg><past><p3><sg>/find<vblex><tv><neg><past><p3><sg>$}$}$
 No rule specified: ^prpers<prn><subj><p3><m><sg>$
 Applying output rule 61 (line 463): бул<VP><fin><tv><past><p3><sg><neg><NOqst><noNF><do><NOitg><NObarjoq> -> ^бул<vP><tv><past><fin><p3><sg><neg><QD><NFD><NOaux>{^бул<v><tv><neg><past><p3><sg>/find<vblex><tv><neg><past><p3><sg>$}$
 Applying output rule 71 (line 536): бул<vP><tv><past><fin><p3><sg><neg><NOqst><noNF><do> -> ^бул<v><tv><neg><past><p3><sg>/find<vblex><tv><neg><past><p3><sg>$
 No rule specified: ^do<vbdo><past>$
 No rule specified: ^not<adv>$
 No rule specified: ^find<vblex><inf>$
 No rule specified: ^.<sent>$
^prpers<prn><subj><p3><m><sg>$ ^do<vbdo><past>$ ^not<adv>$ ^find<vblex><inf>$ ^.<sent>$
^prpers<prn><subj><p3><m><sg>$ ^find<vblex><past>$ ^.<sent>$
UUM-ENG Output:
he did not find

Example 4 (Ablative Case)

  • (uum) кӧктэн → (eng) from sky
    (uum) кӧк<n><abl> → (eng) from<pr>sky<n><sg>
Tagger Output:
^кӧк<n><abl>$^.<sent>$
Lex Output:
^кӧк<n><abl>/sky<n><abl>$^.<sent>/.<sent>$
Transfer Output:
 Applying rule 2 (line 227): ^кӧк<n><abl>/sky<n><abl>$
 Applying rule 18 (line 306): ^кӧк<NP><n><ND><PSD><abl><from><GD>{^кӧк<n><abl>/sky<n><abl>$}$
 Applying rule 28 (line 324): ^кӧк<dP><NP><ND><PD><PSD><abl><from><NOitg><RGD>{^кӧк<NP><n><ND><PSD><abl><from><GD>{^кӧк<n><abl>/sky<n><abl>$}$}$
 -> rule was rejected
 Applying rule 29 (line 325): ^кӧк<dP><NP><ND><PD><PSD><abl><from><NOitg><RGD>{^кӧк<NP><n><ND><PSD><abl><from><GD>{^кӧк<n><abl>/sky<n><abl>$}$}$
 -> rule was rejected
 Applying rule 21 (line 315): ^кӧк<dP><NP><ND><PD><PSD><abl><from><NOitg><RGD>{^кӧк<NP><n><ND><PSD><abl><from><GD>{^кӧк<n><abl>/sky<n><abl>$}$}$
 -> rule was rejected
 Applying rule 22 (line 316): ^кӧк<dP><NP><ND><PD><PSD><abl><from><NOitg><RGD>{^кӧк<NP><n><ND><PSD><abl><from><GD>{^кӧк<n><abl>/sky<n><abl>$}$}$
 -> rule was rejected
 Applying rule 20 (line 314): ^кӧк<dP><NP><ND><PD><PSD><abl><from><NOitg><RGD>{^кӧк<NP><n><ND><PSD><abl><from><GD>{^кӧк<n><abl>/sky<n><abl>$}$}$
 Applying rule 36 (line 367): ^кӧк<DP><NP><ND><PD><PSD><abl><from><NOitg>{^кӧк<dP><NP><ND><PD><PSD><abl><from><NOitg><RGD>{^кӧк<NP><n><ND><PSD><abl><from><GD>{^кӧк<n><abl>/sky<n><abl>$}$}$}$
 Applying output rule 35 (line 367): кӧк<PP><from><NOitg> -> ^кӧк<DP><NP><ND><PD><PSD><abl><from><NOitg>{^кӧк<dP><NP><ND><PD><PSD><abl><from><NOitg><RGD>{^кӧк<NP><n><ND><PSD><abl><from><GD>{^кӧк<n><abl>/sky<n><abl>$}$}$}$
 No rule specified: ^from<pr>$
 Applying output rule 19 (line 314): кӧк<DP><NP><sg><p3><noPOSS><obj><from><NOitg> -> ^кӧк<dP><NP><ND><PD><PSD><abl><from><NOitg><RGD>{^кӧк<NP><n><ND><PSD><abl><from><GD>{^кӧк<n><abl>/sky<n><abl>$}$}$
 Applying output rule 17 (line 306): кӧк<dP><NP><sg><p3><noPOSS><obj><from><NOitg><noREFG> -> ^кӧк<NP><n><ND><PSD><abl><from><GD>{^кӧк<n><abl>/sky<n><abl>$}$
 Applying output rule 1 (line 227): кӧк<NP><NP><sg><noPOSS><obj><from><noREFG> -> ^кӧк<n><abl>/sky<n><abl>$
 No rule specified: ^sky<n><sg>$
 No rule specified: ^.<sent>/.<sent>$

 ^from<pr>$ ^sky<n><sg>$^.<sent>

===== UUM-ENG Output: =====
 from sky

=== Example 5 (Locative Case) ===

* {{transferTest|uum|eng|бахчыда|in sky}}
*: {{transferMorphTest|uum|eng|бахчы{{tag|n}}{{tag|loc}}|in{{tag|pr}}sky{{tag|n}}{{tag|sg}}}}

===== Tagger Output: =====
 ^бахчы<n><loc>$^.<sent>$

===== Lex Output: =====
 ^бахчы<n><loc>/garden<n><loc>$^.<sent>/.<sent>$

===== Transfer Output: =====

 <nowiki> Applying rule 2 (line 227): ^бахчы<n><loc>/garden<n><loc>$
 Applying rule 18 (line 306): ^бахчы<NP><n><ND><PSD><loc><in><GD>{^бахчы<n><loc>/garden<n><loc>$}$
 Applying rule 28 (line 324): ^бахчы<dP><NP><ND><PD><PSD><loc><in><NOitg><RGD>{^бахчы<NP><n><ND><PSD><loc><in><GD>{^бахчы<n><loc>/garden<n><loc>$}$}$
 -> rule was rejected
 Applying rule 29 (line 325): ^бахчы<dP><NP><ND><PD><PSD><loc><in><NOitg><RGD>{^бахчы<NP><n><ND><PSD><loc><in><GD>{^бахчы<n><loc>/garden<n><loc>$}$}$
 -> rule was rejected
 Applying rule 21 (line 315): ^бахчы<dP><NP><ND><PD><PSD><loc><in><NOitg><RGD>{^бахчы<NP><n><ND><PSD><loc><in><GD>{^бахчы<n><loc>/garden<n><loc>$}$}$
 -> rule was rejected
 Applying rule 22 (line 316): ^бахчы<dP><NP><ND><PD><PSD><loc><in><NOitg><RGD>{^бахчы<NP><n><ND><PSD><loc><in><GD>{^бахчы<n><loc>/garden<n><loc>$}$}$
 -> rule was rejected
 Applying rule 20 (line 314): ^бахчы<dP><NP><ND><PD><PSD><loc><in><NOitg><RGD>{^бахчы<NP><n><ND><PSD><loc><in><GD>{^бахчы<n><loc>/garden<n><loc>$}$}$
 Applying rule 36 (line 367): ^бахчы<DP><NP><ND><PD><PSD><loc><in><NOitg>{^бахчы<dP><NP><ND><PD><PSD><loc><in><NOitg><RGD>{^бахчы<NP><n><ND><PSD><loc><in><GD>{^бахчы<n><loc>/garden<n><loc>$}$}$}$
 Applying output rule 35 (line 367): бахчы<PP><in><NOitg> -> ^бахчы<DP><NP><ND><PD><PSD><loc><in><NOitg>{^бахчы<dP><NP><ND><PD><PSD><loc><in><NOitg><RGD>{^бахчы<NP><n><ND><PSD><loc><in><GD>{^бахчы<n><loc>/garden<n><loc>$}$}$}$
 No rule specified: ^in<pr>$
 Applying output rule 19 (line 314): бахчы<DP><NP><sg><p3><noPOSS><loc><in><NOitg> -> ^бахчы<dP><NP><ND><PD><PSD><loc><in><NOitg><RGD>{^бахчы<NP><n><ND><PSD><loc><in><GD>{^бахчы<n><loc>/garden<n><loc>$}$}$
 Applying output rule 17 (line 306): бахчы<dP><NP><sg><p3><noPOSS><loc><in><NOitg><noREFG> -> ^бахчы<NP><n><ND><PSD><loc><in><GD>{^бахчы<n><loc>/garden<n><loc>$}$
 Applying output rule 1 (line 227): бахчы<NP><NP><sg><noPOSS><loc><in><noREFG> -> ^бахчы<n><loc>/garden<n><loc>$
 No rule specified: ^garden<n><sg>$
 No rule specified: ^.<sent>/.<sent>$
^in<pr>$ ^garden<n><sg>$^.<sent>$
UUM-ENG Output:
from sky

Structural Transfer Post-Evaluation

Statistics About Input Files

Number of words in reference: 231
Number of words in test: 236
Number of unknown words (marked with a star) in test: 76
Percentage of unknown words: 32.20 %

Results when removing unknown-word marks (stars)

Edit distance: 238
Word error rate (WER): 103.03 %
Number of position-independent correct words: 35
Position-independent word error rate (PER): 87.01 %

Coverage Tests

TOP UNKNOWN WORDS:
     3 ^да/*да$
     2 ^тʼетти/*тʼетти$
     2 ^тʼетирдилер/*тʼетирдилер$
     2 ^доғуштан/*доғуштан$
     1 ^ӧстӱ/*ӧстӱ$
     1 ^җеннет/*җеннет$
     1 ^эң/*эң$
     1 ^эништилер/*эништилер$
     1 ^энди/*энди$
     1 ^ышхын/*ышхын$
     1 ^ышихындан/*ышихындан$
     1 ^чобанлара/*чобанлара$
     1 ^чобанлар/*чобанлар$
     1 ^чобаллара/*чобаллара$
     1 ^чине/*чине$
     1 ^хырды/*хырды$
     1 ^хутхарды/*хутхарды$
     1 ^хорхундулар/*хорхундулар$
     1 ^хонуштулар/*хонуштулар$
     1 ^хонду/*хонду$
coverage: 130 / 206 (~0.63106796116504854369)
remaining unknown forms: 76