Difference between revisions of "Turkic languages"
Firespeaker (talk | contribs) |
Firespeaker (talk | contribs) |
||
| Line 41: | Line 41: | ||
|rowspan=2| HFST (lexc+twol) |
|rowspan=2| HFST (lexc+twol) |
||
|rowspan=2| development |
|rowspan=2| development |
||
|rowspan=2| 2, |
|rowspan=2| 2,018 |
||
|[[Әуезов corpus|Әуезов]] |
|[[Әуезов corpus|Әуезов]] |
||
|147.5K |
|147.5K |
||
| ~ |
| ~75.5% |
||
|rowspan=2| incubator/apertium-[[ky-kk]] |
|rowspan=2| incubator/apertium-[[ky-kk]] |
||
|rowspan=2| [[User:nathan0n5ire|Nathan]], [[User:Firespeaker|Jonathan]], [[User:Francis Tyers|Fran]] |
|rowspan=2| [[User:nathan0n5ire|Nathan]], [[User:Firespeaker|Jonathan]], [[User:Francis Tyers|Fran]] |
||
Revision as of 19:19, 10 December 2011
The Turkic languages include Turkish, Azeri, Uzbek, Kazakh, Kyrgyz, Tatar, Chuvash, Turkmen, Bashkir, and several dozen other languages. The languages are related with varying levels of mutual intelligibility. Our goal is to enhance MT coverage of them with apertium.
The ultimate master plan involves generating independent finite-state transducers for each language, and then making individual dictionaries and transfer rules for every pair. The current status of these goals is listed below.
Status
Once a transducer has ~80% coverage on a range of corpora we can say it is "working". Over 90% and it can be considered to be "production".
Transducers
| name | Language | ISO 639 | formalism | state | stems | coverage | location | primary authors | |||
|---|---|---|---|---|---|---|---|---|---|---|---|
| -2 | -3 | corpus | words | %cov | |||||||
| trmorph | Turkish | tr |
tur |
SFST | working | SETimes | 4.1M | ~88% | Çağri | ||
| kymorph | Kyrgyz | ky |
kir |
HFST (lexc+twol) | working | 8,555 | azattyk 2010 | 3.4M | ~87% | trunk/apertium-tr-ky | Jonathan, Mirlan, Fran |
| turmorph | Turkish | tr |
tur |
HFST (lexc+twol) | development | 18,227 | SETimes | 4.1M | ~72% | Gianluca | |
| kazmorph | Kazakh | kk
|
kaz
|
HFST (lexc+twol) | development | 2,018 | Әуезов | 147.5K | ~75.5% | incubator/apertium-ky-kk | Nathan, Jonathan, Fran |
| wp 2011-11 | 0.84M | ~59% | |||||||||
| Chuvash | cv |
cuv? |
HFST (lexc+twol) | development | 88 | 88.8K | ~30% | incubator/apertium-cv-ru | Hèctor | ||
| Tatar | tt |
tat |
- | ||||||||
| azmorph | Azerbaijani | az |
aze |
SFST | working? | - | trunk/apertium-tr-az | Gianluca | |||
Turkic-Turkic pairs
Text in italic denotes language pairs under development / in the incubator. Regular text denotes a functioning language pair in trunk, while text in bold denotes a stable well-working language pair.
| tr | az | tk | uz | ky | kk | tt | cv | ba | ug | |
|---|---|---|---|---|---|---|---|---|---|---|
| tr | — | tr-az | tr-ky | tr-cv | ||||||
| az | az-tr | — | ||||||||
| tk | — | |||||||||
| uz | — | |||||||||
| ky | ky-tr | — | ky-kk | |||||||
| kk | — | kk-tt | ||||||||
| tt | tt-kk | — | tt-ba | |||||||
| cv | cv-tr | — | ||||||||
| ba | — | |||||||||
| ug | — |
Pairs with non-Turkic languages
| tr | az | tk | uz | ky | kk | tt | cv | ba | ug | |
|---|---|---|---|---|---|---|---|---|---|---|
| en | tr-en | ky-en | ||||||||
| fr | ||||||||||
| es | ||||||||||
| it | ||||||||||
| ru | cv-ru | |||||||||
| mn | mn-kk |
Tagset
Rough guide to tagsets in various Turkic language transducers, with an eye to keeping stuff that is basically the same tagged the same. In the following table, A stands for Apertium and T stands for TRmorph.
| Phenomenon | Morphology | Description | Tag(s) | Language(s) | Notes |
|---|---|---|---|---|---|
| Case | |||||
| Ablative case | -DAn | Case indicating movement away | <abl> |
Pan-turkic | |
| Tense, aspect, mood | |||||
| Imperative | -ø | Mood for giving orders | <imp>A, <t_imp>T |
Pan-turkic | |
