User:Zu-ann - Revision history

Zu-ann at 16:01, 27 March 2018

2018-03-27T16:01:03Z

Zu-ann at 15:59, 27 March 2018

2018-03-27T15:59:43Z

Zu-ann at 18:57, 24 March 2018

2018-03-24T18:57:02Z

Zu-ann at 18:56, 24 March 2018

2018-03-24T18:56:40Z

Zu-ann: /* Work plan */

2018-03-24T18:22:13Z

Work plan

Zu-ann at 18:17, 24 March 2018

2018-03-24T18:17:45Z

Zu-ann at 17:02, 24 March 2018

2018-03-24T17:02:33Z

Zu-ann at 13:00, 24 March 2018

2018-03-24T13:00:04Z

Zu-ann at 09:17, 23 March 2018

2018-03-23T09:17:32Z

Zu-ann at 08:53, 23 March 2018

2018-03-23T08:53:11Z

@@ Line 14: / Line 14: @@
 |-
 |'''GitHub:''' https://github.com/zu-ann
+|-
 |'''Forked repositories for coding challenge:'''
+|-
-| *https://github.com/zu-ann/apertium-tat
-| *https://github.com/zu-ann/apertium-bak
+| https://github.com/zu-ann/apertium-tat
+|-
-| *https://github.com/zu-ann/apertium-tat-bak
+| https://github.com/zu-ann/apertium-bak
+|-
+| https://github.com/zu-ann/apertium-tat-bak
 |}

@@ Line 14: / Line 14: @@
 |-
 |'''GitHub:''' https://github.com/zu-ann
+|'''Forked repositories for coding challenge:'''
+| *https://github.com/zu-ann/apertium-tat
+| *https://github.com/zu-ann/apertium-bak
+| *https://github.com/zu-ann/apertium-tat-bak
 |}

@@ Line 75: / Line 75: @@
 |5 || 11.06 - 17.06 || adding nouns
 |-
-|6 || 18.06 - 24.06 || adding nouns + Midterm evaluation.
+|6 || 18.06 - 24.06 || adding nouns + Midterm evaluation
 |-
 |7 || 25.06 - 01.07 || adding nouns

@@ Line 63: / Line 63: @@
 |0|| || collecting Tatar and Bashkir corpora, scraping a parallel corpus, making a frequency dictionary
 |-
-|1|| 14.05 - 20.05 || adding basic numerals and postpositions
+|1|| 14.05 - 20.05 || adding numerals, postpositions and conjunctions
 |-
-|2|| 21.05 - 27.05 || adding conjunctions
+|2|| 21.05 - 27.05 || adding pronouns and determiners
 |-
-|3 || 28.05 - 03.06 || adding adverbs
+|3 || 28.05 - 03.06 || adding adjectives and adverbs
 |-
-|4 || 04.06 - 10.06 || adding pronouns and determiners
+|4 || 04.06 - 10.06 || adding adjectives and adverbs
 |-
 | colspan="3" |'''Deliverable #1'''
 |-
-|5 || 11.06 - 17.06 || adding adjectives and adverbs
+|5 || 11.06 - 17.06 || adding nouns
 |-
-|6 || 18.06 - 24.06 || Midterm evaluation.
+|6 || 18.06 - 24.06 || adding nouns + Midterm evaluation.
 |-
-|7 || 25.06 - 01.07 || rowspan="2" | adding nouns
+|7 || 25.06 - 01.07 || adding nouns
 |-
-|8 || 02.07 - 08.07 ||
+|8 || 02.07 - 08.07 || working on disambiguation
 |-
 | colspan="3" | '''Deliverable #2'''
 |-
-|9 || 09.07 - 15.07 || rowspan="3" |adding verbs
+|9 || 09.07 - 15.07 || adding verbs
 |-
-|10 || 16.07 - 22.07 ||
+|10 || 16.07 - 22.07 || adding verbs
 |-
-|11 || 23.07 - 29.07 ||
+|11 || 23.07 - 29.07 || working on disambiguation
 |-
 |12 || 30.07 - 05.08) || Final evaluation. Tidying up, releasing.

@@ Line 43: / Line 43: @@
 ** and printed dictionaries
-* Resources for Bashkir corpora:
+* Resources for Bashkir corpus:
 ** news portals, for example: http://www.bashinform.ru/
-* Resources for Tatar corpora:
+* Resources for Tatar corpus:
 ** news portals, for example: http://tatarstan.ru/
-* Resources for parallel corpora:
+* Resources for parallel corpus:
 ** online newspapers both in Tatar and Bashkir, for example: https://ru.wikipedia.org/wiki/Районные_газеты_Башкортостана,    http://rbsmi.ru/belizv_t/news/ in Tatar and http://rbsmi.ru/belizv_b/news/ in Bashkir
 ** Bible translations http://ibt.org.ru/ru/

@@ Line 27: / Line 27: @@
 == Reasons why Google and Apertium should sponsor it ==
-Tatar and Baskir are closely related languages, but Apertium currently does not offer translations between them, although it exactly specialises on closely related languages. Moreover, the only existing machine translation platform that supports translations between Tatar and Bashkir is Yandex.Translate. It is not free/open-source (so, for example, not everyone can contribute to it) and belongs not to rule-based machine translation. Due to statistical nature of the Yandex.Translate, sometimes its output contains words which were not in the input or which do not even exist. In my opinion, rule based machine translation for this pair, which I am going to develop, can do better in terms of WER. Emplementing this pair will also increase the number of Apertium users, as there are about 6,5 million Tatar speakers and more than 1,2 million Bashkir speakers.
+Tatar and Baskir are closely related languages, but Apertium currently does not offer translations between them, although it exactly specialises on closely related languages. Moreover, the other machine translation platform that supports text translations between Tatar and Bashkir is Yandex.Translate. It is not free/open-source (so, for example, not everyone can contribute to it) and belongs not to rule-based machine translation. Due to statistical nature of the Yandex.Translate, sometimes its output contains words which were not in the input or which do not even exist. In my opinion, rule based machine translation for this pair, which I am going to develop, can do better in terms of WER. Emplementing this pair will also increase the number of Apertium users, as there are about 6,5 million Tatar speakers and more than 1,2 million Bashkir speakers.
 == A description of how and who it will benefit in society ==
@@ Line 35: / Line 35: @@
 == Work plan ==
+'''Available resources'''
+* Dictionaries:
+** GLOSBE Tatar-Bashkir Dictionary https://glosbe.com/tt/ba
+** Russian-Tatar and Tatar-Russian online dictionaries http://www.tatar.com.ru/, http://suzlek.tatarstan.ru/, http://suzlek.antat.ru/
+** Russian-Bashkir and Bashkir-Russian online dictionaries http://huzlek.bashqort.com/
+** and printed dictionaries
+* Resources for Bashkir corpora:
+** news portals, for example: http://www.bashinform.ru/
+* Resources for Tatar corpora:
+** news portals, for example: http://tatarstan.ru/
+* Resources for parallel corpora:
+** online newspapers both in Tatar and Bashkir, for example: https://ru.wikipedia.org/wiki/Районные_газеты_Башкортостана,    http://rbsmi.ru/belizv_t/news/ in Tatar and http://rbsmi.ru/belizv_b/news/ in Bashkir
+** Bible translations http://ibt.org.ru/ru/
+'''Current state'''
+* apertium-tat: coverage ~91%, stems 25,789 (http://wiki.apertium.org/wiki/Apertium-tat)
+* apertium-bak: coverage ~66%, stems 2,524 (http://wiki.apertium.org/wiki/Apertium-bak)
+* apertium-tat-bak.tat-bak.dix: about 2500-2800 words
 {|class="wikitable"

@@ Line 27: / Line 27: @@
 == Reasons why Google and Apertium should sponsor it ==
-Tatar and Baskir are closely related languages, but Apertium currently does not offer translations between them, although it exactly specialises on closely related languages. Moreover, other machine translation platform (Yandex Translator), that support translations between Tatar and Bashkir, is not free/open-source (so, for example, not everyone can contribute to it) and belongs not to rule-based machine translation. Emplementing this pair will also increase the number of Apertium users, as there are about 6,5 million Tatar speakers and more than 1,2 million Bashkir speakers.
+Tatar and Baskir are closely related languages, but Apertium currently does not offer translations between them, although it exactly specialises on closely related languages. Moreover, the only existing machine translation platform that supports translations between Tatar and Bashkir is Yandex.Translate. It is not free/open-source (so, for example, not everyone can contribute to it) and belongs not to rule-based machine translation. Due to statistical nature of the Yandex.Translate, sometimes its output contains words which were not in the input or which do not even exist. In my opinion, rule based machine translation for this pair, which I am going to develop, can do better in terms of WER. Emplementing this pair will also increase the number of Apertium users, as there are about 6,5 million Tatar speakers and more than 1,2 million Bashkir speakers.
 == A description of how and who it will benefit in society ==
@@ Line 78: / Line 78: @@
 '''Technical skills:'''
 *Python (including BeautifulSoup, psycopg (library for PostgreSQL), Flask, Django, pyTelegramBotAPI, familiar with machine learning using numpy, pandas and sklearn)
-* HTML and CSS (also using Bootstrap)
+* HTML and CSS (also using Bootstrap 4)
 * XML, JSON
 * R

@@ Line 32: / Line 32: @@
 There are 6,5 million Tatar speakers and more than 1,2 million Bashkir speakers, who will get an opportunity to automatically translate from Baskir to Tatar, using a stable rule-based machine translator.
-Furthermore, the Bashkir language has a status of a minority language, so the release of the language pair will serve to support and promote this language. Native speakers of Tatar will be able to translate needed information from Bashkir and read it in their native language.
+Furthermore, the Bashkir language has a status of an endangered language, so the release of the language pair will serve to support and promote this language. Native speakers of Tatar will be able to translate needed information from Bashkir and read it in their native language.
 == Work plan ==

@@ Line 18: / Line 18: @@
 == Why is it that you are interested in machine translation and in Apertium? ==
-Apertium is an free/open-source machine translation platform, which gives people the opportunity to get access to a large amount of information in other languages through fast and understandable translation to the language they know. Rule-based machine translation, which is used in Apertium, in contrast to other kinds of machine translation, relies on the linguistic descriptions of languages, grammars and vocabularies, so this is a practical use of the linguistic data we have, and I find it fascinating.
+Apertium is a free/open-source machine translation platform, which gives people the opportunity to get access to a large amount of information in other languages through fast and understandable translation to the language they know. Rule-based machine translation, which is used in Apertium, in contrast to other kinds of machine translation, relies on the linguistic descriptions of languages, grammars and vocabularies, so this is a practical use of the linguistic data we have, and I find it fascinating.
-Furthermore, I believe that all people should have access to a fast and user-friendly translator, which can translate to and from their native language. Unlike many other translation platforms, Apertium works with minority languages, so that speakers of these languages can have machine translations for their native language. I would be happy to have the opportunity to contribute to it.
+Furthermore, I believe that all people should have access to a fast and user-friendly translator, which can translate to and from their native language. Unlike many other translation platforms, Apertium works with minority languages and provides such translator for these languages, so that speakers of these languages can have machine translations for their native language, as well as other people interested in minority languages. I would be happy to have the opportunity to contribute to it.
 == Which of the published tasks are you interested in? What do you plan to do? ==
-I am interested in developing an existing language pair Tatar and Bashkir (Bashkir -> Tatar), which is now in nursery.
+I am planning to developing an existing language pair Tatar and Bashkir (Bashkir -> Tatar), which is now in nursery.
 == Reasons why Google and Apertium should sponsor it ==
-Tatar and Baskir are closely related languages, but Apertium currently does not offer translations between them, although it exactly specialises on closely related languages. Moreover, other machine translation platform (Yandex Translator), that support translations between Tatar and Bashkir, is not free/open-source (so, for example, not everyone can contribute to it) and belongs not to rule-based machine translation. Emplementing this pair will increase the number of Apertium users, as there are about 6,5 million Tatar speakers, more than 1,2 million Bashkir speakers and only one other existing translator for this pair.
+Tatar and Baskir are closely related languages, but Apertium currently does not offer translations between them, although it exactly specialises on closely related languages. Moreover, other machine translation platform (Yandex Translator), that support translations between Tatar and Bashkir, is not free/open-source (so, for example, not everyone can contribute to it) and belongs not to rule-based machine translation. Emplementing this pair will also increase the number of Apertium users, as there are about 6,5 million Tatar speakers and more than 1,2 million Bashkir speakers.
 == A description of how and who it will benefit in society ==
-There are 6,5 million Tatar speakers and more than 1,2 million Bashkir speakers, who will get an opportunity to automatically translate from Baskir to Tatar.
+There are 6,5 million Tatar speakers and more than 1,2 million Bashkir speakers, who will get an opportunity to automatically translate from Baskir to Tatar, using a stable rule-based machine translator.
 Furthermore, the Bashkir language has a status of a minority language, so the release of the language pair will serve to support and promote this language. Native speakers of Tatar will be able to translate needed information from Bashkir and read it in their native language.