User:Oğuz/GSoC 2019 - Revision history

Oğuz: /* Proposal: Bringing 4 language pairs up to release quality */

2019-04-07T13:00:12Z

Proposal: Bringing 4 language pairs up to release quality

2019-04-07T12:56:58Z

Coding Challenge

2019-04-07T12:52:34Z

Proposal: Bringing 4 language pairs up to release quality

2019-04-05T03:00:38Z

Coding Challenge

2019-04-05T02:56:24Z

Resources

2019-04-05T02:55:22Z

Proposal: Bringing 4 language pairs up to release quality

2019-04-03T22:18:53Z

2019-04-02T14:41:02Z

2019-04-02T14:17:20Z

2019-04-02T13:29:04Z

Resources

@@ Line 25: / Line 25: @@
 '''Which of the published tasks are you interested in? What do you plan to do?'''
-My plan is to adopt 4 unreleased language pairs, tur->uig, kir->tur, tat->tur and uzb->tur (in these directions). I'll be working to bring them up to release quality, which will involve writing and refining rules for transfer, expanding dictinaries, testvoc and lexical selection that will result in a valid text in the target language.
+My plan is to adopt 4 unreleased language pairs, tur->uig, kir->tur, tat->tur and uzb->tur (in these directions). I'll be working to bring them up to release quality, which will involve writing and refining rules for transfer, expanding dictionaries, testvoc and lexical selection that will result in a valid text in the target language.
 {{comment|It's kir, not kyr.  Also, a big part of what's involved is [[testvoc]], not just writing and refining rules.  Probably expanding dictionaries is fairly important as well. —[[User:Firespeaker|Firespeaker]] ([[User talk:Firespeaker|talk]]) 04:55, 5 April 2019 (CEST)}}

@@ Line 136: / Line 136: @@
 == Coding Challenge ==
-I will tag 20 sentences for each language pair and write 5 ambiguity rules.
+I will tag 20 sentences for each language pair and write 5 ambiguity rules. I'll put these on github.
 {{comment|where are you putting it? —[[User:Firespeaker|Firespeaker]] ([[User talk:Firespeaker|talk]]) 05:00, 5 April 2019 (CEST)}}

@@ Line 25: / Line 25: @@
 '''Which of the published tasks are you interested in? What do you plan to do?'''
-My plan is to adopt 4 unreleased language pairs, uig-tur, kyr-tur, tat-tur and uzb-tur. I'll be working to bring them up to release quality, which will involve writing and refining rules for transfer and lexical selection that will result in a valid text in the target language.
+My plan is to adopt 4 unreleased language pairs, tur->uig, kir->tur, tat->tur and uzb->tur (in these directions). I'll be working to bring them up to release quality, which will involve writing and refining rules for transfer, expanding dictinaries, testvoc and lexical selection that will result in a valid text in the target language.
 {{comment|It's kir, not kyr.  Also, a big part of what's involved is [[testvoc]], not just writing and refining rules.  Probably expanding dictionaries is fairly important as well. —[[User:Firespeaker|Firespeaker]] ([[User talk:Firespeaker|talk]]) 04:55, 5 April 2019 (CEST)}}

@@ Line 138: / Line 138: @@
 I will tag 20 sentences for each language pair and write 5 ambiguity rules.
+{{comment|where are you putting it? —[[User:Firespeaker|Firespeaker]] ([[User talk:Firespeaker|talk]]) 05:00, 5 April 2019 (CEST)}}
 == Deliverables ==

@@ Line 58: / Line 58: @@
 cevirce.com[http://cevirce.com/] for Turkish-Kyrgyz, Turkish-Uzbek and Turkish-Tatar translations
+{{comment|How do you plan to use these?  Looking up words manually?  Scraping them?  We have pages of resources for some of these languages with sources already listed—so why list them here? —[[User:Firespeaker|Firespeaker]] ([[User talk:Firespeaker|talk]]) 04:56, 5 April 2019 (CEST)}}
 == Work Plan ==

@@ Line 26: / Line 26: @@
 My plan is to adopt 4 unreleased language pairs, uig-tur, kyr-tur, tat-tur and uzb-tur. I'll be working to bring them up to release quality, which will involve writing and refining rules for transfer and lexical selection that will result in a valid text in the target language.
+{{comment|It's kir, not kyr.  Also, a big part of what's involved is [[testvoc]], not just writing and refining rules.  Probably expanding dictionaries is fairly important as well. —[[User:Firespeaker|Firespeaker]] ([[User talk:Firespeaker|talk]]) 04:55, 5 April 2019 (CEST)}}
@@ Line 31: / Line 33: @@
 Apertium hosts numerous MTs of Turkic languages but some of them haven't been worked to completion. By refining these pairs we'd be bringing in these MTs to Apertium repertoire and cover an important ground in Turkic computational linguistics.
 ==Resources==

← Older revision		Revision as of 22:18, 3 April 2019
Line 153:		Line 153:

	I'm a 3rd year student of linguistics at Boğaziçi University. I've taken several compuational linguistics classes as part of my studies. I've already worked with Apertium last year on an MT project between Uyghur and Turkish, which I believe helped me improve my understanding of computational linguistics.		I'm a 3rd year student of linguistics at Boğaziçi University. I've taken several compuational linguistics classes as part of my studies. I've already worked with Apertium last year on an MT project between Uyghur and Turkish, which I believe helped me improve my understanding of computational linguistics.


			[[Category:GSoC 2019 student proposals]]

@@ Line 31: / Line 31: @@
 Apertium hosts numerous MTs of Turkic languages but some of them haven't been worked to completion. By refining these pairs we'd be bringing in these MTs to Apertium repertoire and cover an important ground in Turkic computational linguistics.
 ==Resources==
@@ Line 55: / Line 56: @@
 cevirce.com[http://cevirce.com/] for Turkish-Kyrgyz, Turkish-Uzbek and Turkish-Tatar translations
 == Work Plan ==
@@ Line 101: / Line 103: @@
 '''Plan by Weeks'''
-. 80% coverage
+. All pairs up to 80% coverage
-. Basic CG
+. Basic CG, 82% coverage
-. 84% coverage
+. 83% coverage
-. Transfer
+. Transfer, 84% coverage
-. 86% coverage
+. 85% coverage
-. Transfer, lexical selection, 65% coverage
+. Transfer, lexical selection
-. CG, 80% coverage
+. CG, 86% coverage
-. Transfer, lexsel, 84% coverage
+. Transfer, lexsel, 87% coverage
+. 88% coverage
-. Transfer
 . CG, Transfer
-. Transfer, lexsel, 86% coverage
+. Transfer, lexsel, 89% coverage
-. Transfer, 88% coverage
+. Transfer, lexsel
-. Preparing text for annotation
+. Preparing texts for annotation
+-16. Annotating the corpora, %90 coverage on each pair
--16. Annotating the Uyghur corpus, %90 coverage
 == Coding Challenge ==
 I will tag 20 sentences for each language pair and write 5 ambiguity rules.
 == Deliverables ==
-??
 WER comparable to other inter-Turkic/Romance pairs.
+Implementation of ambiguous rules.
 Data for machine-learned disambiguation.
-??

← Older revision		Revision as of 14:17, 2 April 2019
Line 1:		Line 1:
	GSoC 2019 proposal draft to ~~create~~ ~~and~~ ~~develop Uyghur-Turkish~~ translation ~~pair~~.		GSoC 2019 proposal draft to improve four Turkic translation pairs.

	== Personal Information ==		== Personal Information ==

@@ Line 52: / Line 52: @@
 Pamukkale University's Turkish-Kyrgyz[http://ctle.pau.edu.tr/kgtr/], Turkish-Tatar[http://ctle.pau.edu.tr/tttr/] and Turkish-Uzbek[http://ctle.pau.edu.tr/uztr/] dictionaries
-Indiana University's Uzbek-English dictionary[https://www.indiana.edu/~ctild/Main/Uzbek-EnglishDictionary]
+Indiana University's Uzbek-English dictionary[https://www.indiana.edu/~ctild/Main/Uzbek-EnglishDictionary/]
-cevirce.com[cevirce.com] for Turkish-Kyrgyz, Turkish-Uzbek and Turkish-Tatar translations
+cevirce.com[http://cevirce.com/] for Turkish-Kyrgyz, Turkish-Uzbek and Turkish-Tatar translations
 == Work Plan ==