Apertium has moved from SourceForge to GitHub.
If you have any questions, please come and talk to us on #apertium on irc.freenode.net or contact the GitHub migration team.

Turkic MT Improvements GSoC2019 report

From Apertium
(Difference between revisions)
Jump to: navigation, search
Line 47: Line 47:
   
 
==Dictionaries==
 
==Dictionaries==
All dictionaries were improved in the first stage of the project, with the help of mentors on Kypchak languages.
+
All dictionaries were improved in the first stage of the project, with the help of mentors on Kipchak languages.
   
 
==Disambiguation==
 
==Disambiguation==

Revision as of 09:20, 26 August 2019

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

Contents

Commits

My commits can be found below, on each depository:

Tur-Uzb Tur Uzb Uig-Tur Uig Tur-Tat Tat Tur-Kir Kir

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, 83.5% 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

Dictionaries

All dictionaries were improved in the first stage of the project, with the help of mentors on Kipchak languages.

Disambiguation

To correctly discern the lemma and the morphology so as to be translated correctly into the target language, Apertium uses Constraint Grammar (CG). As part of the project, CG rules were added where necessary. Uzbek and Turkish in particular received extensive attention in this regard.

Future Plans

Uzbek lexicon still needs to be improved. Analysis of Uzbek can be problematic because of the unusual alphabet of the language along with non-standard forms, which also needs further improvement. More lexical selection, disambiguation and transfer rules are needed to achieve a greater translation quality on all pairs.

Personal tools