Turkic MT Improvements GSoC2019 report

From Apertium
Revision as of 10:43, 25 August 2019 by Oğuz (talk | contribs)
Jump to navigation Jump to search

This aim of this project was improving the following language pairs of Apertium: tur->uig, uzb->tur, kir->tur, tat->tur.

Commits

My commits can be found [here]. You can also download my work as a [ zip file].

https://github.com/apertium/apertium-tur-uzb/commits?author=koguzhan https://github.com/apertium/apertium-tur/commits?author=koguzhan https://github.com/apertium/apertium-uzb/commits?author=koguzhan https://github.com/apertium/apertium-uig-tur/commits?author=koguzhan https://github.com/apertium/apertium-uig/commits?author=koguzhan https://github.com/apertium/apertium-tur-tat/commits?author=koguzhan https://github.com/apertium/apertium-tat/commits?author=koguzhan https://github.com/apertium/apertium-tur-kir/commits?author=koguzhan https://github.com/apertium/apertium-kir/commits?author=koguzhan

Transfer

Transfer rules were written for tur->uig and uzb->tur, using Regression Tests. They can be found here: Uighur and Uzbek.


Corpora and Coverage

L Wiki Bible
Tur-Uig 53505239 words, 82.3% cov 178233 words, 93.0% cov
Uzb-Tur 12730161 words, 80.8% cov 184447 words, 81.1% cov
Kir-Tur 11435418 words, 82.5% cov 184808 words, 92.0% cov
Tat-Tur 5792382 words, 86.4% cov 178220 words, 91.4% cov


Disambiguation

To correctly discern the lemma and the morphology so as to be translated correctly into the target language, Apertium uses Constraint Grammar (CG).

Lexical Selection

To determine in which context which translation of a given lemma would be selected, lexical selection is employed.