Difference between revisions of "Turkic-Turkic translator"

From Apertium
Jump to navigation Jump to search
 
(13 intermediate revisions by 3 users not shown)
Line 6: Line 6:
! Pair !! Languages !! Location !! Directions !! Testvoc !! Coverage (%) !! stems !! WER !! WER<nowiki>*</nowiki>
! Pair !! Languages !! Location !! Directions !! Testvoc !! Coverage (%) !! stems !! WER !! WER<nowiki>*</nowiki>
|-
|-
| [[apertium-kaz-tat]] || [[Kazakh]] &mdash; [[Tatar]] || [[trunk]] || <code>kaz-tat</code>, <code>tat-kaz</code> || — || ~{{:Apertium-kaz-tat/stats/kaz-average}}%{{slc|kaz}}, ~{{:Apertium-kaz-tat/stats/tat-average}}%{{slc|tat}} || {{#lst:Apertium-kaz-tat/stats|kaz-tat-stems}} || - || -
| [[apertium-kaz-tat]] || [[Kazakh]] &mdash; [[Tatar]] || [[trunk]] || <code>kaz-tat</code>, <code>tat-kaz</code> || — || ~{{:Apertium-kaz-tat/stats/kaz-average}}%{{slc|kaz}}, ~{{:Apertium-kaz-tat/stats/tat-average}}%{{slc|tat}} || {{#lst:Apertium-kaz-tat/stats|kaz-tat_stems}} || - || -
|-
|-
| [[apertium-tr-az]] || [[Turkish]] &mdash; [[Azeri]] || [[trunk]] || <code>tr-az</code> || - || - || || - || -
| [[apertium-crh-tur]] || [[Turkish]] &mdash; [[Crimean Tatar]] || [[trunk]] || <code>crh-tur</code> || - || - || {{#lst:Apertium-crh-tur/stats|crh-tur_stems}} || - || -
|-
|-
| [[apertium-tur-kir]] || [[Turkish]] &mdash; [[Kyrgyz]] || [[staging]] || <code>tur-kir</code> || - || (<code>tr</code>: 80.39) || || - || -
| [[apertium-kaz-kir]] || [[Kazakh]] &mdash; [[Kyrgyz]] || [[staging]] || <code>kaz-kir</code> || - || - || {{#lst:Apertium-kaz-kir/stats|kaz-kir_stems}} || - || -
|-
|-
| [[apertium-tt-ba]] || [[Tatar]] &mdash; [[Bashkir]] || [[nursery]] || <code>tt-ba</code>, <code>ba-tt</code> || - || - || || - || -
| [[apertium-tur-aze]] || [[Turkish]] &mdash; [[Azeri]] || [[staging]] || <code>tur-aze</code> || - || - || {{#lst:Apertium-tur-aze/stats|tur-aze_stems}} || - || -
|-
|-
| [[apertium-tuk-tur]] || [[Turkmen]] &mdash; [[Turkish]] || [[nursery]] || <code>tuk-tur</code>, <code>tur-tuk</code> || - || - || || - || -
| [[apertium-tur-kir]] || [[Turkish]] &mdash; [[Kyrgyz]] || [[staging]] || <code>tur-kir</code> || - || (<code>tr</code>: 80.39) || {{#lst:Apertium-tur-kir/stats|tur-kir_stems}} || - || -
|-
|-
| [[apertium-tr-tt]] || [[Turkish]] &mdash; [[Tatar]] || [[incubator]] || <code>tr-tt</code>, <code>tt-tr</code> || - || - || || - || -
| [[apertium-tat-bak]] || [[Tatar]] &mdash; [[Bashkir]] || [[nursery]] || <code>tt-ba</code>, <code>ba-tt</code> || - || - || {{#lst:Apertium-tat-bak/stats|tat-bak_stems}} || - || -
|-
|-
| [[apertium-cv-tr]] || [[Chuvash]] &mdash; [[Turkish]] || [[incubator]] || <code>tr-cv</code>, <code>cv-tr</code> || - || - || || - || -
| [[apertium-tuk-tur]] || [[Turkmen]] &mdash; [[Turkish]] || [[nursery]] || <code>tuk-tur</code>, <code>tur-tuk</code> || - || - || {{#lst:Apertium-tuk-tur/stats|tuk-tur_stems}} || - || -
|-
|-
| [[apertium-kaz-kir]] || [[Kazakh]] [[Kyrgyz]] || [[incubator]] || <code>kaz-kir</code> || || ~{{:Apertium-kaz-kir/stats/kaz-average}}%{{slc|kaz}}, ~{{:Apertium-kaz-kir/stats/kir-average}}%{{slc|kir}} ||{{#lst:Apertium-kaz-kir|kaz-kir-stems}} || ||
| [[apertium-tur-tat]] || [[Turkish]] &mdash; [[Tatar]] || [[incubator]] || <code>tr-tt</code>, <code>tt-tr</code> || - || - || {{#lst:Apertium-tur-tat/stats|tur-tat_stems}} || - || -
|-
|-
| [[apertium-tur-uzb]] || [[Turkish]] [[Uzbek]] || [[incubator]] || <code>uzb-tur</code> || || || {{#lst:Apertium-tur-uzb/stats|tur-uzb-stems}} || ||
| [[apertium-cv-tr]] || [[Chuvash]] &mdash; [[Turkish]] || [[incubator]] || <code>tr-cv</code>, <code>cv-tr</code> || - || - || {{#lst:Apertium-chv-tur/stats|chv-tur_stems}} || - || -
|-
| [[apertium-kaz-kir]] || [[Kazakh]] — [[Kyrgyz]] || [[incubator]] || <code>kaz-kir</code> || — || ~{{:Apertium-kaz-kir/stats/kaz-average}}%{{slc|kaz}}, ~{{:Apertium-kaz-kir/stats/kir-average}}%{{slc|kir}} || {{#lst:Apertium-kaz-kir/stats|kaz-kir_stems}} || — || —
|-
| [[apertium-kaz-kaa]] || [[Kazakh]] — [[Karakalpak]] || [[incubator]] || <code>kaz-kaa</code> || — || || {{#lst:Apertium-kaz-kaa/stats|kaz-kaa_stems}} || — || —
|-
| [[apertium-kaz-kum]] || [[Kazakh]] — [[Kumyk]] || [[incubator]] || <code>kaz-kum</code> || — || || {{#lst:Apertium-kaz-kum/stats|kaz-kum_stems}} || — || —
|-
| [[apertium-kaz-uig]] || [[Kazakh]] — [[Uyghur]] || [[incubator]] || <code>kaz-uig</code> || — || || {{#lst:Apertium-kaz-uig/stats|kaz-uig_stems}} || — || —
|-
| [[apertium-tur-uzb]] || [[Turkish]] — [[Uzbek]] || [[incubator]] || <code>uzb-tur</code> || — || — || {{#lst:Apertium-tur-uzb/stats|tur-uzb_stems}} || — || —
|}
|}



Latest revision as of 22:50, 30 October 2017

Status[edit]

Pair Languages Location Directions Testvoc Coverage (%) stems WER WER*
apertium-kaz-tat KazakhTatar trunk kaz-tat, tat-kaz ~88.7%(kaz), ~87%(tat) - -
apertium-crh-tur TurkishCrimean Tatar trunk crh-tur - - - -
apertium-kaz-kir KazakhKyrgyz staging kaz-kir - - ? - -
apertium-tur-aze TurkishAzeri staging tur-aze - - 8,194 - -
apertium-tur-kir TurkishKyrgyz staging tur-kir - (tr: 80.39) 7,123 - -
apertium-tat-bak TatarBashkir nursery tt-ba, ba-tt - - 2,941 - -
apertium-tuk-tur TurkmenTurkish nursery tuk-tur, tur-tuk - - 3,387 - -
apertium-tur-tat TurkishTatar incubator tr-tt, tt-tr - - 3,317 - -
apertium-cv-tr ChuvashTurkish incubator tr-cv, cv-tr - - - -
apertium-kaz-kir KazakhKyrgyz incubator kaz-kir ~87.3%(kaz), ~85.8%(kir) ?
apertium-kaz-kaa KazakhKarakalpak incubator kaz-kaa 5,408
apertium-kaz-kum KazakhKumyk incubator kaz-kum 561
apertium-kaz-uig KazakhUyghur incubator kaz-uig 2,728
apertium-tur-uzb TurkishUzbek incubator uzb-tur 3,519
Notes
  • WER is the idealised word error rate with full coverage on a crafted test set.
  • WER* is the realistic error rate given non-complete coverage.
  • Coverage is the naïve coverage over one or more free corpora.

Work plan[edit]

This is a general workplan for development efforts for Turkic--Turkic prototype translators. Suitable for use in the Google Summer of Code.

  • 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.
Week Dates Trimmed coverage Testvoc Evaluation Notes
0 23/04—21/05 45% <postadv> <ij> 500 words Preliminary evaluation. Translate the story total coverage and without diagnostics (in both directions). Get a baseline WER. Work on disambiguation, the morphological ambiguities in the story should be resolved.
1 21/05—27/05 50% <num> <post> - Basic numerals, and postpositions should be clean.
2 28/05—03/06 53% <cnjcoo> <cnjadv> <cnjsub> -
3 04/06—10/06 59% <adv> 200 words Work on disambiguation.
4 11/06—17/06 63% <prn> <det> -
5 18/06—24/06 68% <adj> <adj><advl> - Adjectives with attributive and adverbial function should be clean. Numerals + affixes should have their phonology solved.
6 25/06—01/07 70% <n> <num><subst> <np> <adj><subst> 500 words Midterm evaluation. Work on disambiguation.
7 02/07—08/07 73% - -
8 09/07—15/07 75% - -
9 16/07—22/07 77% - 200 words Work on disambiguation.
10 23/07—29/07 80% <v> -
11 30/07—05/08 80% - - Work on disambiguation.
12 06/08—12/08 80% all categories clean 500 words Final evaluation. Tidying up, releasing