User:Lylax2/proposal2017 - Revision history

Lylax2 at 08:37, 4 April 2017

2017-04-04T08:37:52Z

Lylax2 at 10:18, 3 April 2017

2017-04-03T10:18:06Z

Show changes

Lylax2: /* Ancillary Goals */

2017-04-01T19:56:29Z

Ancillary Goals

Lylax2: /* Primary Goals */

2017-04-01T19:56:01Z

Primary Goals

Lylax2 at 19:50, 1 April 2017

2017-04-01T19:50:05Z

Lylax2 at 19:47, 1 April 2017

2017-04-01T19:47:42Z

Lylax2 at 19:46, 1 April 2017

2017-04-01T19:46:34Z

Lylax2 at 19:41, 1 April 2017

2017-04-01T19:41:53Z

Show changes

Lylax2 at 16:39, 31 March 2017

2017-03-31T16:39:08Z

Lylax2 at 16:33, 31 March 2017

2017-03-31T16:33:43Z

@@ Line 184: / Line 184: @@
 |-
 |}
+== Coding Challenge ==
+[https://github.com/lylax47/GSOC2017_Coding_Challenge Coding Challenge]
 == Non-GSOC Plans for the Summer ==

@@ Line 65: / Line 65: @@
 * Viable if primary goals are acheived faster than anticipated
 ** Improve accuracy of Rus -> Ces
-*** Ces -> Rus bidix coverage of 80%
+*** Rus -> Ces bidix coverage of 60%
 *** Accuracy of Rus -> Ces < 40 % WER

@@ Line 58: / Line 58: @@
 * Stable release of Ces -> Rus
+** Ces -> Rus Bidix coverage of 95%
 ** Accuracy of Ces -> Rus < 10 % WER
@@ Line 64: / Line 65: @@
 * Viable if primary goals are acheived faster than anticipated
 ** Improve accuracy of Rus -> Ces
-** Accuracy of Rus -> Ces < 40 % WER
+*** Ces -> Rus bidix coverage of 80%
+*** Accuracy of Rus -> Ces < 40 % WER
 === Timeline ===

@@ Line 79: / Line 79: @@
 | 0
 | now - 30/05
-| Find resources for improving the bilingual dictionary. Study Czech grammar. Write Bash scripts for easy alteration, compiling, and measurement. Parse UD-Czech (Script already exists)
+| Find resources for improving the bilingual dictionary. Work on expanding the bil-Dictionary's coverage. Study Czech grammar. Write Bash scripts for easy alteration, compiling, and measurement. Parse UD-Czech (Script already exists)
 |
 * Create a text corpus for various testing phases and progress measurements: 8 Basic(200 words), 2 each for each category (law, academic, literature, spoken, economics, and news)(300 words), 6 advanced(500 words)
+*Improve bidix size to 45% clean in testvoc for all categories
 | This will involve primarily preparing materials for working on the translator. Also, despite already having a solid foundation in Czech grammar, I would still like to improve upon it before I begin.
 |-

@@ Line 123: / Line 123: @@
 * Improve bidix size to 85% clean in testvoc for all categories
 * Achieve WER < 10% on 1 basic text
-* Achieve WER < 20% on 1 advance text
+* Achieve WER < 20% on 1 advanced text
 | Many common constructions are currently absent in the dictionary and in the transfer rules. Seeing as how there is not a huge amount to cover, at this point I would like to access and discuss possibly working on the Rus -> Ces direction. Because of uncertainty, the following plans will assume continual work on the Ces -> Rus direction.
 |-
@@ Line 174: / Line 174: @@
 |
 * Improve bidix size to 95% clean in testvoc for all categories
-* Achieve WER < 10% on all previous advanced texts and 1 new advance texts (6 texts)
+* Achieve WER < 10% on all previous advanced texts and 1 new advanced texts (6 texts)
 | Similar to the previous week. The last month is mostly focused on utilising time as efficiently as possible to create a quality finished product.
 |-

@@ Line 82: / Line 82: @@
 |
 * Create a text corpus for various testing phases and progress measurements: 8 Basic(200 words), 2 each for each category (law, academic, literature, spoken, economics, and news)(300 words), 6 advanced(500 words)
-| This will involve working primarily on I want to have everything ready for Despite already having a solid foundation in Czech grammar, I would still like to improve upon it before I begin.
+| This will involve primarily preparing materials for working on the translator. Also, despite already having a solid foundation in Czech grammar, I would still like to improve upon it before I begin.
 |-
 | 1
@@ Line 94: / Line 94: @@
 | 2
 | 05/06 - 11/06
-| Continue to expand bil-dictionary where needed(constant task), and work on lexical selection. Work on rudimentary transfer rules, as well as those for verbs.
+| Continue to expand bil-dictionary where needed(constant task), and work on lexical selection. Work on rudimentary transfer rules, as well as begin on transfer rules for verbs.
 |
 * Improve bidix size to 60% clean in testvoc for all categories
@@ Line 110: / Line 110: @@
 | 4
 | 19/06 - 25/06
-| Continue work on verbal transfer rules. Work on specific transfer rules for prepositions and subject addition/placement. Create rules for ancillary Russian cases in the mono-dictionary (2nd prepositional(locative), partitive, ect.).
+| Work on specific transfer rules for prepositions and subject addition/placement. Create rules for ancillary Russian cases in the mono-dictionary (2nd prepositional(locative), partitive, ect.).
 |
 * Improve bidix size to 80% clean in testvoc for all categories
@@ Line 172: / Line 172: @@
 |14/08 - 20/08
 | Documentation (will try to do this gradually), final testing and bug fixes
+|
 * Improve bidix size to 95% clean in testvoc for all categories
 * Achieve WER < 10% on all previous advanced texts and 1 new advance texts (6 texts)
@@ Line 179: / Line 180: @@
 |08/21 - 08/29
 | Work on final evaluations and other bureaucratic necessities.
+|
-| Final week. Everything should be ready.
+Done!
+| Final week. Everything should already be ready.
 |-
 |}

@@ Line 73: / Line 73: @@
 | now - 30/05
 | Find resources for improving the bilingual dictionary. Study Czech grammar. Write Bash scripts for easy alteration, compiling, and measurement. Parse UD-Czech (Script already exists)
-| Find texts for testing phases and progress measurements: Basic, categories (law, academic, literature, spoken, and news)
+| Find texts for testing phases and progress measurements: Basic(200 words), categories (law, academic, literature, spoken, and news)(200 words), advanced(500 words)
 | Despite already having a solid foundation in Czech grammar, I would still like to improve upon it before I begin.
 |-
@@ Line 79: / Line 79: @@
 | 30/05 - 04/06
 | Work on expanding the bilingual dictionary, and monolingual dictionaries where necessary. Create a new tagger for Czech. Test tagger.
+| Achieve a
 | The bilingual dictionary has a paucity of entries at the moment. On top of this, Apertium needs a new POS-tagger for Czech, which in its current state leads to unnecessary translation errors.
 |-

@@ Line 53: / Line 53: @@
 === Who it will benefit? ===
 Developing this language pair will be very beneficial to language learners, tourists, academics, translators, as well as businesses and organisations of both countries. Excluding the recent sanctions, ties between Russian and the Czech Republic have been positively trending, especially in the spheres of trade and tourism, making the development of such a language pair increasingly useful for both business and leisure travelers.
+=== Primary Goals ===
+* Stable release of Ces -> Rus
+** Coverage of Ces -> Rus < 10 %
 === Timeline ===
@@ Line 62: / Line 67: @@
 ! Dates
 ! Objective
+! Measures/targets
 ! Comments
 |-
@@ Line 67: / Line 73: @@
 | now - 30/05
 | Find resources for improving the bilingual dictionary. Study Czech grammar. Write Bash scripts for easy alteration, compiling, and measurement. Parse UD-Czech (Script already exists)
+| Find texts for testing phases and progress measurements: Basic, categories (law, academic, literature, spoken, and news)
 | Despite already having a solid foundation in Czech grammar, I would still like to improve upon it before I begin.
 |-
@@ Line 139: / Line 146: @@
 I will be busy before GSOC starts with finishing up my thesis and preparing for my thesis defense. Consequently, I will have less time to prepare for the project (10 hours a week) before the official start date, May 30. Other than this, I will be searching for a job, so I may have to travel for interviews, but this should however not affect my total work hours per week, merely my availability at/on certain times/days.
+[[Category:GSoC 2017 Student Proposals‎|Lylax2]]