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 11: Line 11:
   
 
== Corpora and Coverage ==
 
== Corpora and Coverage ==
  +
   
   
 
{| class="wikitable"
 
{| class="wikitable"
 
|-
 
|-
! Corpus
+
! L
! Words
+
! Wiki
! Coverage
+
! 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, 82.8% cov
|
+
| 184808 words, 93.4% cov
 
|-
 
|-
|
+
| Tat-Tur
|
+
| --
|
+
| 178220 words, 91.4% cov
 
|}
 
|}
   

Revision as of 10:32, 23 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 [here]. You can also download my work as a [ zip file].

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, 82.8% cov 184808 words, 93.4% cov
Tat-Tur -- 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). Currently Uyghur has about 45 CG rules for disambiguation.


Lexical Selection

To determine in which context which translation of a given lemma would be selected, lexical selection is employed. Currently uig-tur has 35 lexsel rules.

Personal tools