Difference between revisions of "Apertium Turkic"

From Apertium
Jump to navigation Jump to search
(→‎Translation pairs: some updates)
(22 intermediate revisions by 2 users not shown)
Line 12: Line 12:
 
=== Approaching production quality ===
 
=== Approaching production quality ===
 
The following pairs are all approaching production quality, but have suffered from stalled development and need various amounts of work to bring to production quality.
 
The following pairs are all approaching production quality, but have suffered from stalled development and need various amounts of work to bring to production quality.
* The '''[[Turkish and Kyrgyz|Turkish-Kyrgyz]]''' pair was developed in the summer of 2011 by Mirlan Ipasov under the supervision of Jonathan, and was our first Turkic-Turkic pair using HFST. Mirlan and Jonathan's work on the Kyrgyz transducer paved the way for other Turkic pairs. The pair needs some work to be brought up to date to work with newer transducers.
+
* The '''[[Kazakh and Kyrgyz|Kazakh-Kyrgyz]]''' pair was originally developed in 2013 by Qantörö under the supervision of Jonathan, and was cleaned up quite a bit by Jonathan in 2014. It works fairly well already, but needs more attention to approach production-level quality.
* The '''[[Kazakh and Kyrgyz|Kazakh-Kyrgyz]]''' pair was originally developed in 2013 by Qantörö under the supervision of Jonathan, and was cleaned up quite a bit by Jonathan in 2014. Should be ready for release soon.
 
* The '''[[Uzbek and Turkish|Uzbek-Turkish]]''' pair was largely developed by Akın under the supervision of Gianluca, but is not yet production-ready.
 
   
 
=== Under development ===
 
=== Under development ===
The following pairs are under active development, but are a ways from being production-ready:
+
The following pairs are under development, but are a ways from being production-ready:
 
* The '''[[English and Kazakh|English-Kazakh]]''' pair is being worked on by Aida Sundetova under the supervision of Mikel Forcada.
 
* The '''[[English and Kazakh|English-Kazakh]]''' pair is being worked on by Aida Sundetova under the supervision of Mikel Forcada.
 
* The '''[[Kazakh and Karakalpak|Qaraqalpaq-Kazakh]]''' pair was originally put together by Atabek, Fran, and Jonathan, and is being developed further by Beknazar.
 
* The '''[[Kazakh and Karakalpak|Qaraqalpaq-Kazakh]]''' pair was originally put together by Atabek, Fran, and Jonathan, and is being developed further by Beknazar.
 
* The '''[[Tatar and Russian|Tatar-Russian]]''' pair is being developed by Ilnar.
 
* The '''[[Tatar and Russian|Tatar-Russian]]''' pair is being developed by Ilnar.
  +
* '''[[Russian and Kazakh|Russian-Kazakh]]'''
  +
* '''[[Crimean Tatar and Turkish|Crimean Tatar-Turkish]]'''
   
 
=== Prototypes ===
 
=== Prototypes ===
Line 34: Line 34:
 
* '''Uzbek-Kyrgyz'''
 
* '''Uzbek-Kyrgyz'''
 
* '''Kazakh-Kumyk'''
 
* '''Kazakh-Kumyk'''
 
* The '''[[Uzbek and Turkish|Uzbek-Turkish]]''' pair was largely developed by Akın under the supervision of Gianluca, but needs more work to be production-ready.
  +
* The '''[[Turkish and Kyrgyz|Turkish-Kyrgyz]]''' pair was developed in the summer of 2011 by Mirlan Ipasov under the supervision of Jonathan, and was our first Turkic-Turkic pair using HFST. Mirlan and Jonathan's work on the Kyrgyz transducer paved the way for other Turkic pairs. The pair needs some work to be brought up to date to work with newer transducers.
   
 
=== Planned for the future ===
 
=== Planned for the future ===
Line 53: Line 55:
 
* [[apertium-kaz-tat|Kazakh-Tatar]] (oversaw development)
 
* [[apertium-kaz-tat|Kazakh-Tatar]] (oversaw development)
 
* [[apertium-tur-kir|Turkish-Kyrgyz]] (oversaw development, cleaned up)
 
* [[apertium-tur-kir|Turkish-Kyrgyz]] (oversaw development, cleaned up)
* [[apertium-kaz-kir|Kazakh-Kyrgyz]] (prototyped, oversaw development, cleaned up)
+
* [[apertium-kaz-kir|Kazakh-Kyrgyz]] (prototyped, oversaw development, constantly cleaning up)
 
* [[apertium-khk-kaz|Khalkha-Kazakh]] (prototyping)
 
* [[apertium-khk-kaz|Khalkha-Kazakh]] (prototyping)
 
* [[apertium-eng-kaz|English-Kazakh]] (occasional consultation)
 
* [[apertium-eng-kaz|English-Kazakh]] (occasional consultation)
Line 68: Line 70:
 
* [[apertium-kaa|Karakalpak]] (developed most of the morphophonology)
 
* [[apertium-kaa|Karakalpak]] (developed most of the morphophonology)
 
* [[apertium-uig|Uyghur]] (developed most of the morphotactics and morphophonology)
 
* [[apertium-uig|Uyghur]] (developed most of the morphotactics and morphophonology)
  +
* [[apertium-crh|Crimean Tatar]] (assisted with morphotactics and lexicon; developed most of the morphophonology)
 
|
 
|
 
* Uzbek-Kyrgyz
 
* Uzbek-Kyrgyz
Line 87: Line 90:
 
|
 
|
 
|-
 
|-
  +
| || Memduh Gökırmak || fotonzade ||
| || Beknazar Abdikamalov<br/>([[User:Beknazar|wiki]]) || beknazar ||
 
* [[apertium-kaz-kaa|Kazakh-Karakalpak]]
+
* [[apertium-crh-tur|Crimean Tatar-Turkish]]
  +
|
  +
|-
  +
| || Sevilay Beyatlı || piraye ||
  +
* [[apertium-kaz-tur|Kazakh-Turkish]]
 
|
 
|
 
|}
 
|}
Line 102: Line 109:
 
* [[apertium-uzb-tur|Uzbek-Turkish]] (oversaw development)
 
* [[apertium-uzb-tur|Uzbek-Turkish]] (oversaw development)
 
|-
 
|-
| || Mirlan Ipasov || gantu || Turkish-Kyrgyz
+
| || Mirlan Ipasov || gantu ||
  +
* Turkish-Kyrgyz
 
|-
 
|-
| || Hèctor Alòs i Font || || Chuvash-Turkish
+
| || Hèctor Alòs i Font || ||
  +
* Chuvash-Turkish
 
|-
 
|-
| || Röstäm Batalov || || Tatar-Bashqort
+
| || Röstäm Batalov || ||
  +
* Tatar-Bashqort
 
|-
 
|-
| || Akın Dalkı || akindalki || Uzbek-Turkish
+
| || Akın Dalkı || akindalki ||
  +
* Uzbek-Turkish
 
|-
 
|-
| || Qantörö Erqulov || kantoro || Kazakh-Kyrgyz
+
| || Qantörö Erqulov || kantoro ||
  +
* Kazakh-Kyrgyz
  +
|-
 
| || Beknazar Abdikamalov<br/>([[User:Beknazar|wiki]]) || beknazar ||
  +
* [[apertium-kaz-kaa|Kazakh-Karakalpak]]
 
|}
 
|}
   
Line 124: Line 139:
   
 
== About our website ==
 
== About our website ==
The [http://turkic.apertium.org/ turkic.apertium.org] website is powered by [[apertium-apy]] and [[apertium-html-tools]], both written and developed largely by Sushain as part of GCI 2013. It runs on a virtualhost donated to us by [http://www.bytemark.co.uk/ Bytemark].
+
The [http://turkic.apertium.org/ turkic.apertium.org] website is powered by [[apertium-apy]] and [[apertium-html-tools]], both written and developed originally by Sushain as part of GCI 2013. It runs on a virtualhost donated to us by [http://www.bytemark.co.uk/ Bytemark].
   
 
== Publications ==
 
== Publications ==
   
  +
* Washington, Jonathan (2017). [http://open.edu.kg/KY/oer-summer-camp-presentations/ Эркин/ачык булактуу тил технологиялары кыргыз жана тектеш тилдер үчүн / Free/Open-Source language technologies for Kyrgyz and beyond]
* Washington, Jonathan N., Ilnar Salimzyanov, and Francis M. Tyers. (2014) "''Designing finite-state morphological transducers for Kypchak languages''". Proceedings of [http://www.indiana.edu/~mrphfest/ MorphologyFest: Symposium on Morphological Complexity]. '''[http://svn.code.sf.net/p/apertium/svn/branches/papers/kypchak-morphfest-2014/poster.pdf Poster]'''
 
  +
  +
* Washington et al. (2016). RodYaz [http://rodyaz.ru/avtomaticheskaia-obrabotka-teksta-no4] / [http://rodyaz.ru/pdf/no.4_2016/Washington%20J.,%20Bayyr-ool%20A.,%20Salchak%20A.,%20Tyers%20F.%20Development%20of%20a%20finite-state%20model%20for%20morphological%20processing%20of%20Tuvan.pdf]
  +
  +
* Tyers et al. (2016). LREC [http://www.lrec-conf.org/proceedings/lrec2016/summaries/1009.html]
  +
  +
* Zhenisbek et al. (2016). CICLing/TurCLing
  +
  +
* Tyers, Francis and Jonathan Washington (2015). "[http://turklang.antat.ru/proceedings.pdf#page=277 Towards a free/open-source Universal Dependency treebank for Kazakh]" ([http://svn.code.sf.net/p/apertium/svn/branches/papers/2015-turklang-kazdep/paper.pdf pre-published version]). In Proceedings of [http://turklang.antat.ru/ Turklang 2015, Kazan, September 17–19, 2015].
  +
  +
* Tyers, Francis, Tommi Pirinen, Jonathan Washington (2015). "Finite-state morphologies and text corpora as resources for improving morphological descriptions". [https://sites.google.com/site/compmorphon2015/ Workshop on Computational Phonology and Morphology]. [http://svn.code.sf.net/p/apertium/svn/branches/papers/2015-compmorphon-morphver/poster.pdf Poster presentation].
  +
  +
* Abduali, Balzhan, Akhmadieva Zhadyra, Zholdybekova Saule, Tukeyev Ualsher, Rakhimova Diana (2015). [http://xixona.dlsi.ua.es/~mlf/apertium-turklang-2015-papers/turklang2015-rakhimova.pdf Study of the problem of creating structural transfer rules and lexical selection for the Kazakh-Russian machine translation system on Apertium platform] In Proceedings of [http://turklang.antat.ru/ Turklang 2015, Kazan, September 17–19, 2015].
  +
  +
* Sundetova, Aida, Mikel Forcada, Francis Tyers (2015). [http://xixona.dlsi.ua.es/~mlf/apertium-turklang-2015-papers/turklang2015-sundetova.pdf A free/open-source machine translation system for English to Kazakh] In Proceedings of [http://turklang.antat.ru/ Turklang 2015, Kazan, September 17–19, 2015].
  +
  +
* Amirova, Dina (2015). [http://xixona.dlsi.ua.es/~mlf/apertium-turklang-2015-papers/turklang2015-amirova.pdf Choosing the model for solving the problem of lexical selection for English-Kazakh language pair in the free/open-source platform Apertium] In Proceedings of [http://turklang.antat.ru/ Turklang 2015, Kazan, September 17–19, 2015].
  +
  +
* Karibayeva, Aidana (2015). [http://xixona.dlsi.ua.es/~mlf/apertium-turklang-2015-papers/turklang2015-karibayeva.pdf Lexical selection rules for Kazakh-to-English machine translation in the free/open-source platform Apertium] In Proceedings of [http://turklang.antat.ru/ Turklang 2015, Kazan, September 17–19, 2015].
  +
 
* Washington, Jonathan N., Ilnar Salimzyanov, and Francis M. Tyers. (2014) "''Designing finite-state morphological transducers for Kypchak languages''". Proceedings of [http://www.indiana.edu/~mrphfest/ MorphologyFest: Symposium on Morphological Complexity]. '''[http://svn.code.sf.net/p/apertium/svn/branches/papers/2014-morphfest-kypchak/poster.pdf Poster]'''
   
* Washington, Jonathan N., Ilnar Salimzyanov, and Francis M. Tyers. (2014) "''Finite-state morphological transducers for three Kypchak languages''". Proceedings of the 9th Conference on Language Resources and Evaluation, LREC2014. '''[http://svn.code.sf.net/p/apertium/svn/branches/papers/kipchak-lrec-2013/poster/poster.pdf Poster]''', '''[http://svn.code.sf.net/p/apertium/svn/branches/papers/kipchak-lrec-2013/kipchak-paper.pdf Paper]'''
+
* Washington, Jonathan N., Ilnar Salimzyanov, and Francis M. Tyers. (2014) "''Finite-state morphological transducers for three Kypchak languages''". Proceedings of the 9th Conference on Language Resources and Evaluation, LREC2014. '''[http://svn.code.sf.net/p/apertium/svn/branches/papers/2013-lrec-kipchak/poster/poster.pdf Poster]''', '''[http://svn.code.sf.net/p/apertium/svn/branches/papers/2013-lrec-kipchak/kipchak-paper.pdf Paper]''', '''[http://www.lrec-conf.org/proceedings/lrec2014/summaries/1207.html Paper in proceedings]'''
   
 
* Salimzyanov, Ilnar, Jonathan Washington, and Francis Tyers (2013). ''A free/open-source Kazakh-Tatar machine translation system''. [http://www.mtsummit2013.info/main_proceedings.asp MT Summit XIV]. '''[http://www.mtsummit2013.info/files/proceedings/main/mt-summit-2013-salimzyanov-et-al.pdf Paper]'''
 
* Salimzyanov, Ilnar, Jonathan Washington, and Francis Tyers (2013). ''A free/open-source Kazakh-Tatar machine translation system''. [http://www.mtsummit2013.info/main_proceedings.asp MT Summit XIV]. '''[http://www.mtsummit2013.info/files/proceedings/main/mt-summit-2013-salimzyanov-et-al.pdf Paper]'''

Revision as of 06:08, 11 August 2017

The Apertium Turkic working group includes everyone who works on Turkic-language resources as part of the Apertium project. Resources we develop include not just Machine Translation systems, but their underlying components which can be repurposed, including morphological transducers, disambiguators, and dictionaries.

You can browse our projects, evaluate our publications, see a list of our contributors, or contact us about a mistake you noticed, a project you'd like to see, or your interest in helping out. Our work is showcased at turkic.apertium.org.

Translation pairs

We have done quite a bit of work on Machine Translation systems involving Turkic languages. This section provides a short overview of some of them, roughly in order of how well they work. For more detail on the current status of various resources, see our Turkic languages page.

Released

  • Our Kazakh-Tatar system was developed largely by Ilnar, who did the majority of work on it as his GSoC 2012 project. The project was overseen by Jonathan, who did a lot of work on the transducers (especially Kazakh), and Fran. The system was deemed production-ready and released during summer of 2013, and work is ongoing to increase its accuracy.

Approaching production quality

The following pairs are all approaching production quality, but have suffered from stalled development and need various amounts of work to bring to production quality.

  • The Kazakh-Kyrgyz pair was originally developed in 2013 by Qantörö under the supervision of Jonathan, and was cleaned up quite a bit by Jonathan in 2014. It works fairly well already, but needs more attention to approach production-level quality.

Under development

The following pairs are under development, but are a ways from being production-ready:

Prototypes

The following pairs are prototypes that could blossom if given proper attention.

  • The Tatar-Bashqort pair was developed by Röstäm, Ilnar, Jonathan, and Fran. It has very promising results as a prototype system, but the Bashqort transducer still needs a lot of work.
  • Chuvash-Turkish
  • The Khalkha-Kazakh pair has been being developed by Jonathan for fun. He's currently looking for a someone who knows Khalkha well to contribute.
  • Chuvash-Tatar
  • Tatar-Turkish
  • The Azeri-Turkish pair was originally developed by Gianluca, but azmorph has since become obsolete.
  • The Turkmen-Turkish pair needs some attention.
  • The Kazakh-Uyghur pair was thrown together by Fran and Jonathan with some assistance from Märdan.
  • Uzbek-Kyrgyz
  • Kazakh-Kumyk
  • The Uzbek-Turkish pair was largely developed by Akın under the supervision of Gianluca, but needs more work to be production-ready.
  • The Turkish-Kyrgyz pair was developed in the summer of 2011 by Mirlan Ipasov under the supervision of Jonathan, and was our first Turkic-Turkic pair using HFST. Mirlan and Jonathan's work on the Kyrgyz transducer paved the way for other Turkic pairs. The pair needs some work to be brought up to date to work with newer transducers.

Planned for the future

There are pairs that Apertium Turkic developers would like to see exist at some point.

  • Qaraqalpaq-Uzbek
  • Kazakh-Nogay

People

Active contributors

Photo Name IRC nick Turkic projects involved in (role) Other Turkic projects interested in
Spectie.260.jpg
Francis Morton Tyers
(wiki · email)
spectie, spectei, spectre
Jonathan at Gullfoss 2.jpg
Jonathan North Washington
(wiki · email)
firespeaker, jonorthwash, kd5cfx

Pairs:

Transducers:

  • Kazakh (developed much of morphotactics and morphophonology)
  • Kyrgyz (developed almost entirety of morphotactics and morphophonology)
  • Tatar (helped develop morphotactics and morphophonology)
  • Bashqort (helped develop morphotactics and morphophonology)
  • Chuvash (helped develop morphotactics and morphophonology)
  • Turkmen (helped develop morphotactics and morphophonology)
  • Kumyk (helped develop morphotactics and morphophonology)
  • Nogay (helped develop morphotactics and morphophonology)
  • Karakalpak (developed most of the morphophonology)
  • Uyghur (developed most of the morphotactics and morphophonology)
  • Crimean Tatar (assisted with morphotactics and lexicon; developed most of the morphophonology)
  • Uzbek-Kyrgyz
  • Qaraqalpaq-Uzbek
  • More South-Siberian Turkic languages!
Ilnar Salimzyanov
(wiki · email)
selimcan
  • Tatar-Bashqort
Mlf-photo.jpg
Mikel Forcada mlforcada
Aida Sundetova Aida
Memduh Gökırmak fotonzade
Sevilay Beyatlı piraye

Inactive contributors

The following contributors are not currently active, but their participation is always welcome!

Photo Name IRC nick Turkic projects involved in (role)
Zfe.jpg
Gianluca Grossi
(wiki)
zfe
Mirlan Ipasov gantu
  • Turkish-Kyrgyz
Hèctor Alòs i Font
  • Chuvash-Turkish
Röstäm Batalov
  • Tatar-Bashqort
Akın Dalkı akindalki
  • Uzbek-Turkish
Qantörö Erqulov kantoro
  • Kazakh-Kyrgyz
Beknazar Abdikamalov
(wiki)
beknazar

Other contributors

Photo Name IRC nick Contributions
Sushain Cherivirala sushain, sushain97 apertium-apy, apertium-html-tools

We also appreciate the assistance of everyone who's helped with localising apertium-html-tools.

About our website

The turkic.apertium.org website is powered by apertium-apy and apertium-html-tools, both written and developed originally by Sushain as part of GCI 2013. It runs on a virtualhost donated to us by Bytemark.

Publications

  • Washington et al. (2016). RodYaz [1] / [2]
  • Tyers et al. (2016). LREC [3]
  • Zhenisbek et al. (2016). CICLing/TurCLing
  • Washington, Jonathan N., Ilnar Salimzyanov, and Francis M. Tyers. (2014) "Finite-state morphological transducers for three Kypchak languages". Proceedings of the 9th Conference on Language Resources and Evaluation, LREC2014. Poster, Paper, Paper in proceedings
  • Salimzyanov, Ilnar, Jonathan Washington, and Francis Tyers (2013). A free/open-source Kazakh-Tatar machine translation system. MT Summit XIV. Paper
  • Tyers, Francis, Ilnar Salimzyanov, Jonathan Washington, and Rustam Batalov (2012): "A proto-type Bashkir-Tatar machine translation system". LREC 2012. Slides

Contact

Feel free to contact us if you find a mistake, there's a project you would like to see us work on, or you would like to help out.

To contact the Apertium Turkic team, you can find us on apertium's IRC channel, send one of us a message through the wiki, or send an email to contact@turkic.apertium.org — don't worry, we're friendly :)

We maintain a low-traffic mailing list (apertium-turkic@lists.sourceforge.net) where occasional discussion and announcements occur. See our archives or subscribe to join in on the fun!