Difference between revisions of "Uighur and Turkish/Paper"

From Apertium
Jump to navigation Jump to search
Line 32: Line 32:
 
* [https://ci.nii.ac.jp/naid/110002911592 Paraphrasing Japanese Words to Expand a Japanese - Uighur Bilingual Dictionary ]
 
* [https://ci.nii.ac.jp/naid/110002911592 Paraphrasing Japanese Words to Expand a Japanese - Uighur Bilingual Dictionary ]
 
* [https://www.jstage.jst.go.jp/article/jnlp1994/8/3/8_3_123/_article/-char/ja/ Conversion process of case particles for Japanese-Uighur machine translation] - There is an english version of this above
 
* [https://www.jstage.jst.go.jp/article/jnlp1994/8/3/8_3_123/_article/-char/ja/ Conversion process of case particles for Japanese-Uighur machine translation] - There is an english version of this above
Turkish:
+
'''Turkish''':
 
* [https://polen.itu.edu.tr/xmlui/bitstream/handle/11527/527/10459.pdf?sequence=1&isAllowed=y Uygurcadan Türkçeye bilgisayarlı çeviri.] [https://scholar.googleusercontent.com/scholar.bib?q=info:zmL5BQqzH04J:scholar.google.com/&output=citation&scisig=AAGBfm0AAAAAWzsR0fI2a0hOeD13Uc1ofWmW8gYQMlf6&scisf=4&ct=citation&cd=-1&hl=tr BibTex] - We should probably find and cite this, and also look into the other stuff Orhun/Tantuğ/Adalı have been up to.
 
* [https://polen.itu.edu.tr/xmlui/bitstream/handle/11527/527/10459.pdf?sequence=1&isAllowed=y Uygurcadan Türkçeye bilgisayarlı çeviri.] [https://scholar.googleusercontent.com/scholar.bib?q=info:zmL5BQqzH04J:scholar.google.com/&output=citation&scisig=AAGBfm0AAAAAWzsR0fI2a0hOeD13Uc1ofWmW8gYQMlf6&scisf=4&ct=citation&cd=-1&hl=tr BibTex] - We should probably find and cite this, and also look into the other stuff Orhun/Tantuğ/Adalı have been up to.
 
* [https://polen.itu.edu.tr/handle/11527/518 Akraba Ve Bitişken Diller Arasında Bilgisayarlı Çeviri İçin Karma Bir Model] [https://scholar.googleusercontent.com/scholar.bib?q=info:5rSIKuO_cR4J:scholar.google.com/&output=citation&scisig=AAGBfm0AAAAAWzsVAXD0j27q7UXvnKrisWh5Eft5EKd8&scisf=4&ct=citation&cd=-1&hl=tr BibTeX] This also has Turkmen-Turkish as a prototype, lacks lexsel. The prose seems to sacrifice intelligibility for the sake of using words with Turkic roots. <s>Also has a corpus of around a million words that we might be able to get our hands on.</s> Seems to be a turkish corpus
 
* [https://polen.itu.edu.tr/handle/11527/518 Akraba Ve Bitişken Diller Arasında Bilgisayarlı Çeviri İçin Karma Bir Model] [https://scholar.googleusercontent.com/scholar.bib?q=info:5rSIKuO_cR4J:scholar.google.com/&output=citation&scisig=AAGBfm0AAAAAWzsVAXD0j27q7UXvnKrisWh5Eft5EKd8&scisf=4&ct=citation&cd=-1&hl=tr BibTeX] This also has Turkmen-Turkish as a prototype, lacks lexsel. The prose seems to sacrifice intelligibility for the sake of using words with Turkic roots. <s>Also has a corpus of around a million words that we might be able to get our hands on.</s> Seems to be a turkish corpus
 
* [http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.614.5731&rep=rep1&type=pdf Rule Based Analysis of the Uyghur Nouns] [https://scholar.googleusercontent.com/scholar.bib?q=info:IPwR6tYl7u8J:scholar.google.com/&output=citation&scisig=AAGBfm0AAAAAW0Wr46dRPOwCNffhZ3f09Pmh96Cv0DwQ&scisf=4&ct=citation&cd=-1&hl=tr BibTex]
 
* [http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.614.5731&rep=rep1&type=pdf Rule Based Analysis of the Uyghur Nouns] [https://scholar.googleusercontent.com/scholar.bib?q=info:IPwR6tYl7u8J:scholar.google.com/&output=citation&scisig=AAGBfm0AAAAAW0Wr46dRPOwCNffhZ3f09Pmh96Cv0DwQ&scisf=4&ct=citation&cd=-1&hl=tr BibTex]
  +
* [https://tez.yok.gov.tr/UlusalTezMerkezi YÖK] Thesis #290286: Description of tatar morphology and a Tatar-Turkish machine translation system / Tatarcanın morfolojisinin tanımlanması ve Tatarca-Türkçe makine çeviri sistemi - ERCAN GÖKGÖZ
   
 
==== Other ====
 
==== Other ====

Revision as of 10:58, 13 August 2018

Info related to paper on uig-tur RBMT.

TO DO

  • Fill out latex template
  • Evaluate system on corpora

To write

  • Intro
  • Evals

Images and Diagrams

Related Work

SEARCH ON CNKI + GOOGLE TRANSLATE

Uyghur-specific

Chinese-Uyghur

Japanese-Uyghur

Non-english Research

Japanese: Muhtar Muhsut seems to have worked a lot on japanese-uighur translation in japanese universities.

Turkish:

Other

Turkic

Fun

Tangentially Related

Evaluations

Since there seem to have been a number of prototypes, mostly for Chinese-Uyghur, it might make sense to compare these values with any evaluation those systems may have, and also the Turkic Apertium pairs crh-tur, kaz-tur, kaz-tat and gag-tur.

  • Adalı &co seem to have worked a good bit on Uyghur analysis and disambiguation, so that would also be a good thing to compare.

WER

BLEU

Various Potential Corpora

Examples