User:Qavan

Information

Name: Nikolay Aleksandrov
University: I. N. Ulianov Chuvash State University
E-mail address: pro100qavan@gmail.com
IRC: qavan
Location: Cheboxary, Russia
Timezone: UTC+3
Telegram: @qavan
GitHub: https://github.com/qavan

Why is it that you are interested in machine translation and in Apertium?

Apertium as an open source system is of great interest to me because of its ability to take into account many factors of the language that other interpreters do not take into account. I will work for the benefit of society, that's great. I'm surprised by the system itself, because before that I did not see translators with Chuvash language who could work so flexibly.

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

I am planning to developing an existing language pair Chuvash-Russian (Chuvash <-> Russian), which is now in nursery. Also I will working on improving Chuvash-Tatar translator.

Reasons why Google and Apertium should sponsor it

The sponsorship of Google gives an excellent motivation to work on projects in which, unfortunately, few enthusiasts come to work. And for Apertium, this is an excellent opportunity to notice people who can help make their work better and bring something new.

A description of how and who it will benefit in society

Currently, there is a problem of ousting the Chuvash language in Chuvashia. Since the chance to find among themselves a "common language" in Russian is much more likely, even though the Chuvash language speakers are much more. This is a big problem at the moment.

List your skills and qualifications

I am a 3rd-year bachelor student of Chuvash State University, Russia. Technical skills:Python, Pascal, any SQL, WEB(HTML,CSS,JS)
Languages: Chuvash, Russian, English

Current state:

apertium-rus: coverage ~89.6%, stems ~170,000(?)
apertium-chv: coverage ~90%, stems ~45,000(?)
apertium-chv-rus.chv-rus.dix: about ~75 words

Work plan

Available resources

Dictionaries

Russian-Chuvash and Chuvash-Russian online dictionaries
http://ru.samah.chv.su
https://chuvash-republic.ru
https://translate.academic.ru/
http://www.classes.ru
https://glosbe.com/ru/cv/
https://glosbe.com/ru/cv
printed dictionaries
and some others(coming soon)

Resources for corpus

wiki dumps

Resources for parallel corpus

online newspapers both in Chuvash and Russian, for example: https://ru.wikipedia.org/wiki/Районные_газеты_Чувашии
articles
and some others(coming soon)
Plan

Week	Dates	Actions
?	previous	coding challenge, community bonding
1	27.05 - 02.06	working on numerals, postpositions and conjunctions
2	03.06 - 09.06	working on pronouns and determiners
3	10.06 - 16.06	working on adjectives and adverbs
4	17.06 - 23.06	working on adjectives and adverbs
5	24.06 - 30.06	working on nouns + First Evaluations
6	01.07 - 07.07	working on nouns
7	08.07 - 14.07	working on nouns
8	15.07 - 21.07	working on disambiguation
9	22.07 - 28.07	working on verbs + Second Evaluations
10	29.07 - 04.08	working on verbs
11	05.08 - 11.08	working on disambiguation
12	12.08 - 18.08	road2release
13	19.08 - 26.08	Final evaluation.
Project completed!

List your skills and qualifications

I am a 3rd-year bachelor student of Chuvash State University, Russia. Technical skills: Python, Pascal, any SQL, WEB(HTML,CSS,JS)
Languages: Chuvash, Russian, English.

Non-Summer-of-Code plans you have for the Summer

In first two week of June I will have to take exams. So I will be able to work less time in the mentioned this weeks(~30). And the rest of the time I will devote to the development of an translator.