Kazakh and Tatar/TODO - Revision history

Ilnar.salimzyan: /* General TODO */

2015-08-31T21:20:27Z

General TODO

2015-08-31T21:19:56Z

General TODO

2015-08-19T21:22:18Z

2014-03-16T13:23:28Z

clean up some of the outdated parts

2014-02-02T21:07:07Z

Goals

2014-02-02T12:18:57Z

Goals

2014-01-29T18:43:15Z

General TODO

2014-01-29T14:55:11Z

2013-09-15T19:29:16Z

2013-07-01T19:07:22Z

General TODO

@@ Line 40: / Line 40: @@
 * Consider ''турындагы'' - should it still be tagged as postposition?
 * How to handle verbs with inner inflection (sometimes a Kazakh verb is translated with a multiword and vice versa. E.g. ''әуреле > башын әйләндер'')
-* past.evid
+* a better default translation for Kazakh past.evid
 === Algorithm for checking dictionaries (as part of the testvocing) ===

@@ Line 40: / Line 40: @@
 * Consider ''турындагы'' - should it still be tagged as postposition?
 * How to handle verbs with inner inflection (sometimes a Kazakh verb is translated with a multiword and vice versa. E.g. ''әуреле > башын әйләндер'')
+* past.evid
 === Algorithm for checking dictionaries (as part of the testvocing) ===

@@ Line 1: / Line 1: @@
 == Goals ==
-In both directions: apertium-kaz-tat has at least 15000 top stems, 95% coverage on all the corpora we have, and no more than 15% Word-Error-Rate on any randomly selected text. It has full coverage on '''Абай жолы. Бірінші кітап''' and disambiguates it fully with at least 90% of precision. There is a unified and documented testing framework to test morphotactics (specs for each [[Turkic_lexicon#Morphotactics|type II LEXICON]]), morphophonology, coverage, CG performance, regression and pending tests targeted mainly at transfer rules, a “gold standard” parallel corpus to measure the WER and to always have something to work on. Testvoc is clean.
+In both directions: apertium-kaz-tat has at least 15000 top stems, 95% coverage on all the corpora we have, and no more than 15% Word-Error-Rate on any randomly selected text. It has full coverage on '''Абай жолы. Бірінші кітап''' and disambiguates it fully with at least 90% of precision. There is a unified and documented testing framework to test morphotactics (specs for each [[Turkic_lexicon#Morphotactics|type II LEXICON]]), morphophonology, coverage, CG performance, regression and pending tests targeted mainly at transfer rules, a “gold standard” parallel corpus to measure the WER and to always have something to work on. Tests are fast (slow parts are decoupled). Testvoc is clean.
 == Road map ==

@@ Line 1: / Line 1: @@
 == Goals ==
-In both directions: apertium-kaz-tat has at least 15000 top stems, 95% coverage on all the corpora we have, and no more than 15% Word-Error-Rate on any randomly selected text. It has full coverage on '''Абай жолы. Бірінші кітап''' and disambiguates it fully with at least 90% of precision. There is a unified and documented testing framework to test morphotactics (specs for each [[Turkic_lexicon#Morphotactics|type II LEXICON]]), morphophonology, coverage, CG performance, regression and pending tests targeted mainly at transfer rules, a “gold standard” parallel corpus to measure the WER and to always have something to work on.
+In both directions: apertium-kaz-tat has at least 15000 top stems, 95% coverage on all the corpora we have, and no more than 15% Word-Error-Rate on any randomly selected text. It has full coverage on '''Абай жолы. Бірінші кітап''' and disambiguates it fully with at least 90% of precision. There is a unified and documented testing framework to test morphotactics (specs for each [[Turkic_lexicon#Morphotactics|type II LEXICON]]), morphophonology, coverage, CG performance, regression and pending tests targeted mainly at transfer rules, a “gold standard” parallel corpus to measure the WER and to always have something to work on. Testvoc is clean.
 == Road map ==

@@ Line 10: / Line 10: @@
 See [[Kazakh and Tatar/Work_plan]] and [[Kazakh and Tatar/Remaining unanalysed forms]]
+* Tatar coverage 90%
+* s/fut3/vol/
 * <s>'''0 itself and numbers containing it aren't analyzed (in both directions)'''</s>
 ** <s>This is only true for the transducers in apertium-kaz-tat, apertium-kaz and apertium-tat ones work fine.</s>

@@ Line 23: / Line 23: @@
 * <code>көр%<v%>%<tv%>%<imp%>%<p2%>%<sg%>:гөр # ; ! "" Dir/LR</code> get's trimmed
 * ма не - мыни thing
+* handle gna_cond + DA<postadv> issue in lexc, not in CG
 * Handle the sentences from the paper in transfer, not in CG