Difference between revisions of "Uyghur and English/Structural Transfer"
From LING073
(→Post-Evaluation) |
|||
| (15 intermediate revisions by the same user not shown) | |||
| Line 1: | Line 1: | ||
scrapeTransferTests -p uig-eng "Uyghur_and_English/Contrastive_Grammar" | scrapeTransferTests -p uig-eng "Uyghur_and_English/Contrastive_Grammar" | ||
| − | cat uig.tests.txt | apertium -d ../ling073-uig uig-eng > uig-eng.tests.txt | + | cat uig.tests.txt | apertium -d ../ling073-uig-eng uig-eng > uig-eng.tests.txt |
apertium-eval-translator-line -r eng.tests.txt -t uig-eng.tests.txt | apertium-eval-translator-line -r eng.tests.txt -t uig-eng.tests.txt | ||
| − | = | + | echo "" | apertium -d . uig-eng-lex | rtx-proc -T uig-eng.rtx.bin |
| − | + | ||
| + | =Pre-Evaluation= | ||
| + | |||
Statistics about input files | Statistics about input files | ||
| + | |||
------------------------------------------------------- | ------------------------------------------------------- | ||
| − | Number of words in reference: | + | |
| − | Number of words in test: | + | Number of words in reference: 55 |
| − | Number of unknown words (marked with a star) in test: | + | |
| − | Percentage of unknown words: | + | Number of words in test: 41 |
| + | |||
| + | Number of unknown words (marked with a star) in test: 0 | ||
| + | |||
| + | Percentage of unknown words: 0.00 % | ||
| + | |||
Results when removing unknown-word marks (stars) | Results when removing unknown-word marks (stars) | ||
| + | |||
------------------------------------------------------- | ------------------------------------------------------- | ||
| − | Edit distance: | + | |
| − | Word error rate (WER): | + | Edit distance: 54 |
| + | |||
| + | Word error rate (WER): 98.18 % | ||
| + | |||
Number of position-independent correct words: 2 | Number of position-independent correct words: 2 | ||
| − | Position-independent word error rate (PER): | + | |
| − | </ | + | Position-independent word error rate (PER): 96.36 % |
| + | |||
| + | =Post-Evaluation= | ||
| + | |||
| + | We chose to implement several of the most common noun cases. | ||
| + | |||
| + | Example Sentences: | ||
| + | |||
| + | چېلەك يىقىلدى | ||
| + | |||
| + | چېلەكنىڭ ئۈستى | ||
| + | |||
| + | بۇنىڭ ئۈستى | ||
| + | |||
| + | ئۇ چېلەككە يىقىلدى | ||
| + | |||
| + | ئۇ چېلەكنى ياراتتى | ||
| + | |||
| + | ئۇ چېلەكتە تۇراتتى | ||
| + | |||
| + | ئۇ چېلەكتىن چىقتى | ||
| + | |||
| + | Gold Standard: | ||
| + | |||
| + | the bucket fell | ||
| + | |||
| + | the bucket's top | ||
| + | |||
| + | the top of this | ||
| + | |||
| + | he fell to the bucket | ||
| + | |||
| + | he created the bucket | ||
| + | |||
| + | he lived in the bucket | ||
| + | |||
| + | he emerged from the bucket | ||
| + | |||
| + | ==Results== | ||
| + | |||
| + | ===tagger=== | ||
| + | ^چېلەك<n><nom>$ ^يىقىل<vblex><past><p3>$ | ||
| + | ^چېلەك<n><gen>$ ^ئۈستى<n><nom>$ | ||
| + | ^بۇ<prn><dem><gen>$ ^ئۈستى<n><nom>$ | ||
| + | ^ئۇ<prn><dem><nom>$ ^چېلەك<n><dat>$ ^يىقىل<vblex><past><p3>$ | ||
| + | ^ئۇ<prn><dem><nom>$ ^چېلەك<n><acc>$ ^يارات<vblex><past><p3>$ | ||
| + | ^ئۇ<prn><dem><nom>$ ^چېلەك<n><loc>$ ^تۇر<vblex><impf><past><p3>$ | ||
| + | ^ئۇ<prn><dem><nom>$ ^چېلەك<n><abl>$ ^چىق<vblex><past><p3>$ | ||
| + | |||
| + | ===lex=== | ||
| + | ^چېلەك<n><nom>/bucket<n><nom>$ ^يىقىل<vblex><past><p3>/fall<vblex><past><p3>$ | ||
| + | ^چېلەك<n><gen>/bucket<n><gen>$ ^ئۈستى<n><nom>/top<n><nom>$ | ||
| + | ^بۇ<prn><dem><gen>/this<prn><dem><gen>$ ^ئۈستى<n><nom>/top<n><nom>$ | ||
| + | ^ئۇ<prn><pers><p3><sg><nom>/he<prn><pers><p3><m><sg><nom>$ ^چېلەك<n><dat>/bucket<n><dat>$ ^يىقىل<vblex><past><p3>/fall<vblex><past><p3>$ | ||
| + | ^ئۇ<prn><pers><p3><sg><nom>/he<prn><pers><p3><m><sg><nom>$ ^چېلەك<n><acc>/bucket<n><acc>$ ^يارات<vblex><past><p3>/create<vblex><past><p3>$ | ||
| + | ^ئۇ<prn><pers><p3><sg><nom>/he<prn><pers><p3><m><sg><nom>$ ^چېلەك<n><loc>/bucket<n><loc>$ ^تۇرات<vblex><past><p3>/live<vblex><past><p3>$ | ||
| + | ^ئۇ<prn><pers><p3><sg><nom>/he<prn><pers><p3><m><sg><nom>$ ^چېلەك<n><abl>/bucket<n><abl>$ ^چىق<vblex><past><p3>/emerge<vblex><past><p3>$ | ||
| + | |||
| + | ===transfer=== | ||
| + | ^the<det><def><sg>$ ^bucket<n><sg>$ ^fall<vblex><past><p3>$ | ||
| + | ^the<det><def><sg>$ ^bucket<n><sg><gen>$ ^top<n><sg>$ | ||
| + | ^this<prn><dem><gen>$ ^the<det><def><sg>$ ^top<n><sg>$ | ||
| + | ^he<prn><pers><p3><m><sg><nom>$ ^to<pr>$ ^the<det><def><sg>$ ^bucket<n><sg>$ ^fall<vblex><past><p3>$ | ||
| + | ^he<prn><pers><p3><m><sg><nom>$ ^the<det><def><sg>$ ^bucket<n><sg>$ ^create<vblex><past><p3>$ | ||
| + | ^he<prn><pers><p3><m><sg><nom>$ ^in<pr>$ ^the<det><def><sg>$ ^bucket<n><sg>$ ^live<vblex><past><p3>$ | ||
| + | ^he<prn><pers><p3><m><sg><nom>$ ^from<pr>$ ^the<det><def><sg>$ ^bucket<n><sg>$ ^emerge<vblex><past><p3>$ | ||
| + | |||
| + | ===uig-eng=== | ||
| + | the bucket #fall | ||
| + | the bucket's top | ||
| + | #this the top | ||
| + | #he to the bucket #fall | ||
| + | #he the bucket #create | ||
| + | #he in the bucket #live | ||
| + | #he from the bucket #emerge | ||
| + | |||
| + | ==Statistics== | ||
| + | Statistics about input files | ||
| + | ------------------------------------------------------- | ||
| + | Number of words in reference: 56 | ||
| + | Number of words in test: 55 | ||
| + | Number of unknown words (marked with a star) in test: 0 | ||
| + | Percentage of unknown words: 0.00 % | ||
| + | |||
| + | Results when removing unknown-word marks (stars) | ||
| + | ------------------------------------------------------- | ||
| + | Edit distance: 34 | ||
| + | Word error rate (WER): 60.71 % | ||
| + | Number of position-independent correct words: 32 | ||
| + | Position-independent word error rate (PER): 42.86 % | ||
| + | |||
[[Category:Sp25_StructuralTransfer]] | [[Category:Sp25_StructuralTransfer]] | ||
Latest revision as of 01:03, 12 May 2025
scrapeTransferTests -p uig-eng "Uyghur_and_English/Contrastive_Grammar"
cat uig.tests.txt | apertium -d ../ling073-uig-eng uig-eng > uig-eng.tests.txt
apertium-eval-translator-line -r eng.tests.txt -t uig-eng.tests.txt
echo "" | apertium -d . uig-eng-lex | rtx-proc -T uig-eng.rtx.bin
Contents
Pre-Evaluation
Statistics about input files
Number of words in reference: 55
Number of words in test: 41
Number of unknown words (marked with a star) in test: 0
Percentage of unknown words: 0.00 %
Results when removing unknown-word marks (stars)
Edit distance: 54
Word error rate (WER): 98.18 %
Number of position-independent correct words: 2
Position-independent word error rate (PER): 96.36 %
Post-Evaluation
We chose to implement several of the most common noun cases.
Example Sentences:
چېلەك يىقىلدى
چېلەكنىڭ ئۈستى
بۇنىڭ ئۈستى
ئۇ چېلەككە يىقىلدى
ئۇ چېلەكنى ياراتتى
ئۇ چېلەكتە تۇراتتى
ئۇ چېلەكتىن چىقتى
Gold Standard:
the bucket fell
the bucket's top
the top of this
he fell to the bucket
he created the bucket
he lived in the bucket
he emerged from the bucket
Results
tagger
^چېلەك<n><nom>$ ^يىقىل<vblex><past><p3>$ ^چېلەك<n><gen>$ ^ئۈستى<n><nom>$ ^بۇ<prn><dem><gen>$ ^ئۈستى<n><nom>$ ^ئۇ<prn><dem><nom>$ ^چېلەك<n><dat>$ ^يىقىل<vblex><past><p3>$ ^ئۇ<prn><dem><nom>$ ^چېلەك<n><acc>$ ^يارات<vblex><past><p3>$ ^ئۇ<prn><dem><nom>$ ^چېلەك<n><loc>$ ^تۇر<vblex><impf><past><p3>$ ^ئۇ<prn><dem><nom>$ ^چېلەك<n><abl>$ ^چىق<vblex><past><p3>$
lex
^چېلەك<n><nom>/bucket<n><nom>$ ^يىقىل<vblex><past><p3>/fall<vblex><past><p3>$ ^چېلەك<n><gen>/bucket<n><gen>$ ^ئۈستى<n><nom>/top<n><nom>$ ^بۇ<prn><dem><gen>/this<prn><dem><gen>$ ^ئۈستى<n><nom>/top<n><nom>$ ^ئۇ<prn><pers><p3><sg><nom>/he<prn><pers><p3><m><sg><nom>$ ^چېلەك<n><dat>/bucket<n><dat>$ ^يىقىل<vblex><past><p3>/fall<vblex><past><p3>$ ^ئۇ<prn><pers><p3><sg><nom>/he<prn><pers><p3><m><sg><nom>$ ^چېلەك<n><acc>/bucket<n><acc>$ ^يارات<vblex><past><p3>/create<vblex><past><p3>$ ^ئۇ<prn><pers><p3><sg><nom>/he<prn><pers><p3><m><sg><nom>$ ^چېلەك<n><loc>/bucket<n><loc>$ ^تۇرات<vblex><past><p3>/live<vblex><past><p3>$ ^ئۇ<prn><pers><p3><sg><nom>/he<prn><pers><p3><m><sg><nom>$ ^چېلەك<n><abl>/bucket<n><abl>$ ^چىق<vblex><past><p3>/emerge<vblex><past><p3>$
transfer
^the<det><def><sg>$ ^bucket<n><sg>$ ^fall<vblex><past><p3>$ ^the<det><def><sg>$ ^bucket<n><sg><gen>$ ^top<n><sg>$ ^this<prn><dem><gen>$ ^the<det><def><sg>$ ^top<n><sg>$ ^he<prn><pers><p3><m><sg><nom>$ ^to<pr>$ ^the<det><def><sg>$ ^bucket<n><sg>$ ^fall<vblex><past><p3>$ ^he<prn><pers><p3><m><sg><nom>$ ^the<det><def><sg>$ ^bucket<n><sg>$ ^create<vblex><past><p3>$ ^he<prn><pers><p3><m><sg><nom>$ ^in<pr>$ ^the<det><def><sg>$ ^bucket<n><sg>$ ^live<vblex><past><p3>$ ^he<prn><pers><p3><m><sg><nom>$ ^from<pr>$ ^the<det><def><sg>$ ^bucket<n><sg>$ ^emerge<vblex><past><p3>$
uig-eng
the bucket #fall the bucket's top #this the top #he to the bucket #fall #he the bucket #create #he in the bucket #live #he from the bucket #emerge
Statistics
Statistics about input files ------------------------------------------------------- Number of words in reference: 56 Number of words in test: 55 Number of unknown words (marked with a star) in test: 0 Percentage of unknown words: 0.00 %
Results when removing unknown-word marks (stars) ------------------------------------------------------- Edit distance: 34 Word error rate (WER): 60.71 % Number of position-independent correct words: 32 Position-independent word error rate (PER): 42.86 %
