Difference between revisions of "Apertium-uzb-kaa"
Jump to navigation
Jump to search
(eye opening numbas) |
m |
||
| Line 47: | Line 47: | ||
|- |
|- |
||
--> |
--> |
||
* Corpus testvoc := cat <txt> | apertium-uzb-kaa/testvoc/corpus/trimmed-coverage.sh {uzb-kaa,kaa-uzb}. Corpora can be found [https://github.com/taruen/apertiumpp/tree/master/data4apertium/corpora here]. |
|||
* Number of stems taken from the header "aperium-dixtools format-1line 10 55 apertium-uzb-kaa.uzb-kaa.dix" produces. |
|||
Revision as of 21:36, 26 May 2019
Work plan
- Trimmed coverage means the coverage of both of the morphological analysers after being trimmed according to the bilingual dictionary of the pair, that is, only containing stems which are also in the bilingual dictionary.
- Testvoc for a category means that the category is testvoc clean, in both translation directions.
- Evaluation is taking words and performing an evaluation for post-edition word error rate (WER). The output for those words should be clean.
- Bidix: number of stems in the bilingual dictionary
- Corpus testvoc := cat <txt> | apertium-uzb-kaa/testvoc/corpus/trimmed-coverage.sh {uzb-kaa,kaa-uzb}. Corpora can be found here.
- Number of stems taken from the header "aperium-dixtools format-1line 10 55 apertium-uzb-kaa.uzb-kaa.dix" produces.
| Week | Dates | Bidix goal | Achieved? | Corpus testvoc uzb->kaa (no *, no */@, no */@/# errors) | Corpus testvoc kaa->uzb (no *, no */@, no */@/# errors) | Evaluation | Notes |
|---|---|---|---|---|---|---|---|
| 0 | 20/05—26/05 | 412 | -- | jam(17.7, 17.7, 14.8) udhr(6.1, 6.1, 4.1) bible(9.6, 9.6, 8.2) | jam(34.1, 33.5, 16.2) udhr(n.a. in kaa) bible(17.0, 16.7, 9.7) | -- | |
| 1 | 27/05—02/06 | 5412 | |||||
| 2 | 03/06—09/06 | 10412 | |||||
| 3 | 10/06—16/06 | 15412 | |||||
| 4 | 17/06—23/06 | 20412 |
