Difference between revisions of "Kazakh and Tatar"
Jump to navigation
Jump to search
Firespeaker (talk | contribs) |
Firespeaker (talk | contribs) |
||
| Line 5: | Line 5: | ||
* The [[Apertium-kaz|Kazakh transducer]] has {{#lst:apertium-kaz/stats|stems}} stems and [[apertium-kaz/stats|~{{:apertium-kaz/stats/average}}%]] coverage over random corpora |
* The [[Apertium-kaz|Kazakh transducer]] has {{#lst:apertium-kaz/stats|stems}} stems and [[apertium-kaz/stats|~{{:apertium-kaz/stats/average}}%]] coverage over random corpora |
||
* The [[Apertium-tat|Tatar transducer]] has {{#lst:apertium-tat/stats|stems}} stems and [[apertium-tat/stats|~{{:apertium-tat/stats/average}}%]] coverage over random corpora |
* The [[Apertium-tat|Tatar transducer]] has {{#lst:apertium-tat/stats|stems}} stems and [[apertium-tat/stats|~{{:apertium-tat/stats/average}}%]] coverage over random corpora |
||
| + | |||
| + | === Demonstration === |
||
| + | <code>$ echo "бұл аударушымен татарша жазылған тексттер қазақша аударып оқыса болады" | apertium -d . kaz-tat |
||
| + | бу аударучы белән татарча язылган *тексттер казакъча аударып укыша була</code> (hrm) |
||
== Installation == |
== Installation == |
||
Revision as of 21:20, 21 January 2013
This is a language pair translating between Kazakh and Tatar. The pair is currently located in incubator, but it is expected that it will soon be moved to staging.
General information
- The Kazakh transducer has 36,595 stems and ~94.5% coverage over random corpora
- The Tatar transducer has 55,702 stems and ~91% coverage over random corpora
Demonstration
$ echo "бұл аударушымен татарша жазылған тексттер қазақша аударып оқыса болады" | apertium -d . kaz-tat
бу аударучы белән татарча язылган *тексттер казакъча аударып укыша була (hrm)
Installation
You will need:
- hfst (svn ≥r1916)
- foma
- flex
- foma
- apertium
- lttoolbox
Developers
Information on what remains to be done for this pair can be found at the /TODO list.
Development workflow
We work on the transducers (apertium-kaz and apertium-tat) individually, and use a special process to import to the pair transducers that contain only the words found in the bidix. The following documents this process:
- …
