User:Beknazar/Application

From Apertium
Jump to navigation Jump to search

Contact information

Name: Abdikamalov Beknazar

E-mail address: beknazar23[at]gmail.com

IRC: beknazar

Why is it you are interested in machine translation?

I believe that machine translation is one of the most important areas for humanity by giving people opportunity to share knowledge in various languages. Especially, in the future I am planning to work on machine translation of lesser-known languages in order to let those language users acquire similar amount of knowledge as popular language users.

Why is it that you are interested in the Apertium project?

The main reason is that I consider Apertium as one of the best open source projects on machine translation area. Also, I found out that Apertium focuses on lesser-resourced and marginalised languages and it give me extra inspiration to work in this project.

Which of the published tasks are you interested in? What do you plan to do?

Title

Adopting an unreleased language pair of Kazakh <-> Karakalpak languages.

Reasons why Google and Apertium should sponsor it

There is no other single translator between these two languages despite their similarities. Also, this project would open new ways for Karakalpak language to connect with other languages as well, since currently its coverage level is quite low: ~ 45 %.

A description of how and who it will benefit in society

Firstly, it would be a great help to Karakalpak language speakers, due to UNESCO it’s status considered as vulnerable. The reason for its lower status is that not enough attention is being given to the projects in Karakalpak language.

Work plan

Community bonding period (April 21 - May 19):

  • Getting closer with Apertium tools and community
  • Finding the language resources for Karakalpak and Kazakh
  • Begin editing Kazakh <-> Karakalpak dictionary
  • Studying the existing kaz-tat, kaz-kir, kaz-eng monodices, bidix and transfer rules in order to understand similarities among Turkic based languages

Work Period (May 19 - August 18)

Week 1:

  • Begin creating Karakalpak monodix using Kazakh monodix to its size.
  • Check kaa monodix

Week 2:

  • Check kaa monodix

Week 3:

  • Check kaa monodix

Week 4:

  • Check kaa monodix

Deliverable #1: updated kaa monodix

Week 5:

  • Check and add nouns to kaa monodix, adding new entries to kaz-kaa bidix and adding necessary kaz-kaa transfer rules

Week 6:

  • Check kaa monodix

Week 7 (Midterm June 23 - June 27):

  • Check kaa monodix

Deliverable #2: updated kaa monodix, kaz-kaa bidix and kaz-kaa transfer rules

Week 8:

  • Check kaa, kaz monodix

Week 9:

  • Check kaa, kaz monodix

Week 10:

  • Check kaa, kaz monodix

Deliverable #3: finished kaa monodix, updated kaz monodix, kaz-kaa bidix and kaz-kaa transfer rules

Week 11:

  • testing

Week 12:

  • testing

Week 13:

  • testing

Project completion (August 6 - August 13):

  • Tidying up, releasing

Final evaluation (August 13 - August 18)

List your skills and give evidence of your qualifications

I am on the 3th year of Bachelor’s degree in Computer Science and Engineering at the Ulsan National Institute of Science and Technology (South Korea).

My native language is Karakalpak [Kaa] and I know Kazakh language on a good level too, mainly due to their similarity.

Programming skills: C, C++, Java, Python, git and xml.

List any non-Summer-of-Code plans you have for the Summer

I have no non-GSoC plans for the summer and can contribute from 30 to 40 hours a week. However, my school finishes in the middle of June. Therefore, if it is fine I would like to work ~ 20 hours in the first month and in the 2nd & 3rd months I will work ~ 50 hours per week in order to compensate.