Difference between revisions of "Chechen/Transducer"
From LING073
(Created page with "Transducer on Github: https://github.swarthmore.edu/Ling073-sp19/ling073-che.git ==Note== ==Evaluation== Category:Sp18_Transducers") |
|||
| Line 1: | Line 1: | ||
Transducer on Github: https://github.swarthmore.edu/Ling073-sp19/ling073-che.git | Transducer on Github: https://github.swarthmore.edu/Ling073-sp19/ling073-che.git | ||
==Note== | ==Note== | ||
| + | All 73 tests in che.yaml file passed. | ||
| + | ===Hard-coded Forms=== | ||
| + | {{morphTest|йоӏ{{tag|n}}{{tag|cl_j}}{{tag|abs}}{{tag|pl}}|мехкарий}}: girl, girls | ||
| + | {{morphTest|стаг{{tag|n}}{{tag|cl_j2}}{{tag|abs}}{{tag|pl}}|нах}}: person, people | ||
| + | These forms are hard-coded because they are irregular plural forms, which do not conform to any rule. | ||
| + | |||
| + | {{morphTest|а{{tag|conj}}|а}}: and | ||
| + | This form also hard-coded because there is no morphological change at all for conjunction class. | ||
| + | |||
| + | ===Additional Top Words=== | ||
| + | {|class="wikitable sortable" | ||
| + | ! Top Words !! Coverage Before !! Coverage After | ||
| + | |- | ||
| + | ! N/A | ||
| + | | -- || 1.59% | ||
| + | |- | ||
| + | ! {{morphTest|а{{tag|conj}}|а}} | ||
| + | | 1.59% || 15.73% | ||
| + | |- | ||
| + | ! {{morphTest|ала{{tag|v}}{{tag|iv}}{{tag|past}}{{tag|rem}}{{tag|wit}}|элира}} | ||
| + | | 15.73% || 17.03% | ||
| + | |- | ||
| + | ! {{morphTest|латта{{tag|v}}{{tag|iv}}{{tag|pres}}|лаьтта}} | ||
| + | | 17.03% || 18.23% | ||
| + | |- | ||
| + | ! {{morphTest|Дала{{tag|np}}{{tag|abs}}{{tag|sg}}|Дала}} | ||
| + | | 18.23% || 20.45% | ||
| + | |- | ||
| + | ! {{morphTest|масса{{tag|n}}{{tag|cl_j2}}{{tag|erg}}{{tag|sg}}|массо}} | ||
| + | | 20.45% || 21.27% | ||
| + | |- | ||
| + | ! {{morphTest|иза{{tag|prn}}{{tag|pers}}{{tag|p3}}{{tag|pl}}{{tag|abs}}|иза}} | ||
| + | | 21.27% || | ||
| + | |- | ||
| + | ! {{morphTest|уьш{{tag|prn}}{{tag|pers}}{{tag|p3}}{{tag|pl}}{{tag|abs}}|уьш}} | ||
| + | | || | ||
| + | |- | ||
| + | ! {{morphTest|и{{tag|prn}}{{tag|dem}}{{tag|dst}}|и}} | ||
| + | | || | ||
| + | |- | ||
| + | !{{morphTest|тайпа{{tag|n}}{{tag|cl_d}}{{tag|dat}}{{tag|sg}}|тайпана}} | ||
| + | | || | ||
| + | |} | ||
| + | |||
| + | |||
==Evaluation== | ==Evaluation== | ||
| + | *Total number of stems in the transducer: 55 | ||
| + | *Current coverage over your combined corpus: 24.17% | ||
| + | *The current list of top unknown words returned by <code>aq-covtest</code>: | ||
| + | :*64 т | ||
| + | :*60 у | ||
| + | :*37 х | ||
| + | :*22 Веза | ||
| + | :*21 д | ||
| + | :*20 Т | ||
| + | :*20 аккха | ||
| + | :*18 е | ||
| + | :*18 ехь | ||
| + | :*18 ера | ||
| + | :*15 ду | ||
| + | :*12 к | ||
| + | :*12 хир | ||
| + | :*12 аьлла | ||
| + | :*11 хи | ||
| + | :*11 дерриге | ||
| + | :*11 адам | ||
| + | :*10 де | ||
| + | :*10 Иштта | ||
| + | :*10 цу | ||
| + | *Number of tests that pass in yaml files | ||
| + | :* In che.yaml: 73/73 pass | ||
| + | :* In commonwords.yaml: 7/33 pass | ||
[[Category:Sp18_Transducers]] | [[Category:Sp18_Transducers]] | ||
Revision as of 08:03, 22 February 2019
Transducer on Github: https://github.swarthmore.edu/Ling073-sp19/ling073-che.git
Note
All 73 tests in che.yaml file passed.
Hard-coded Forms
йоӏ<n><cl_j><abs><pl> ↔ мехкарий: girl, girls стаг<n><cl_j2><abs><pl> ↔ нах: person, people These forms are hard-coded because they are irregular plural forms, which do not conform to any rule.
а<conj> ↔ а: and This form also hard-coded because there is no morphological change at all for conjunction class.
Additional Top Words
| Top Words | Coverage Before | Coverage After |
|---|---|---|
| N/A | -- | 1.59% |
| а<conj> ↔ а | 1.59% | 15.73% |
| ала<v><iv><past><rem><wit> ↔ элира | 15.73% | 17.03% |
| латта<v><iv><pres> ↔ лаьтта | 17.03% | 18.23% |
| Дала<np><abs><sg> ↔ Дала | 18.23% | 20.45% |
| масса<n><cl_j2><erg><sg> ↔ массо | 20.45% | 21.27% |
| иза<prn><pers><p3><pl><abs> ↔ иза | 21.27% | |
| уьш<prn><pers><p3><pl><abs> ↔ уьш | ||
| и<prn><dem><dst> ↔ и | ||
| тайпа<n><cl_d><dat><sg> ↔ тайпана |
Evaluation
- Total number of stems in the transducer: 55
- Current coverage over your combined corpus: 24.17%
- The current list of top unknown words returned by
aq-covtest:
- 64 т
- 60 у
- 37 х
- 22 Веза
- 21 д
- 20 Т
- 20 аккха
- 18 е
- 18 ехь
- 18 ера
- 15 ду
- 12 к
- 12 хир
- 12 аьлла
- 11 хи
- 11 дерриге
- 11 адам
- 10 де
- 10 Иштта
- 10 цу
- Number of tests that pass in yaml files
- In che.yaml: 73/73 pass
- In commonwords.yaml: 7/33 pass
