Difference between revisions of "User:Mathematic-alpha/gsoc-progress"

From Apertium
Jump to navigation Jump to search
 
(26 intermediate revisions by 3 users not shown)
Line 104: Line 104:
 
* Write articles for the byv-wiki
 
* Write articles for the byv-wiki
   
== Period ==
+
== Log ==
  +
{|class="wikitable" style="float: right;"
  +
|-
  +
!colspan="4"| Medumba progress
  +
|-
  +
! Date
  +
! byv lexicon size
  +
! Corpus size
  +
! Coverage
  +
|-
  +
| 12.06.2019
  +
| 189
  +
| 8674
  +
| ~0.37
  +
|-
  +
| 20.06.2019
  +
| 317
  +
| 8674
  +
| ~0.39
  +
|-
  +
|-
  +
| 05.07.2019
  +
| 317
  +
| 8674
  +
| ~0.56
  +
|-
  +
|-
  +
| 10.07.2019
  +
| 1186
  +
| 6604
  +
| ~0.83
  +
|-
  +
| 2019-07-21
  +
| 1703
  +
| 22627
  +
| ~65.21%
  +
|-
  +
| 2019-07-25
  +
| 1705
  +
| 22637
  +
| ~69.19%
  +
|-
  +
| 2019-07-25
  +
| 17594
  +
| 22624
  +
| ~77.77%
  +
|-
  +
| 2019-08-05
  +
| 27896
  +
| 35035
  +
| ~79.62%
  +
|}
  +
  +
{|class="wikitable" style="float: right;"
  +
|-
  +
!colspan="4"| Medumba-French progress
  +
|-
  +
! Date
  +
! byv-fra lexicon size
  +
! Coverage
  +
! WER, PER
  +
|-
  +
| 12.06.2019
  +
| 1592
  +
| ~0.10
  +
| Something
  +
|-
  +
| 05.07.2019
  +
| 1592
  +
| ~0.20
  +
| Something
  +
|-
  +
|-
  +
| 10.07.2019
  +
| 1592
  +
| ~0.35
  +
| Something
  +
|}
  +
  +
   
 
=== Community bonding===
 
=== Community bonding===
Line 112: Line 191:
 
* Sort words from corpus by frequency
 
* Sort words from corpus by frequency
 
* Run the first test of the analyser and see what coverage do we achieve with 1800 entries.
 
* Run the first test of the analyser and see what coverage do we achieve with 1800 entries.
  +
Report :
  +
1000 words in the corpus.<br>
  +
So the work has to be continued<br>
  +
Repo : [https://github.com/math-alpha/apertium-byv-fra Apertium-byv-fra]
  +
  +
==== Week 20 - 25 May ====
  +
  +
Objectives :
  +
* Have 10000 words of byv-fra corpus
  +
* Sort words from corpus by frequency
  +
* Run the first test of the analyser and see what coverage do we achieve with 1800 entries.
  +
  +
Result: 2500 BYV entries
  +
  +
==== Week 26 May - 2 June ====
  +
  +
Objectives :
  +
* Continuation
  +
  +
Result:
  +
6000 BYV words in the corpus
  +
  +
==== Week 3 - 9 June ====
  +
Objectives :
  +
  +
==== Week 10 - 16 June ====
  +
Objectives :
  +
  +
==== Week 17 - 23 June ====
  +
Objectives :
  +
  +
==== Week 24 - 30 June (First evaluation)====
  +
  +
Objectives: Fix the morphological analyser to recognise more words
  +
  +
==== Week 1 July - 7 July ====
  +
Objectives : Make both dictionaries even so as to increase byv-fra coverage
  +
  +
==== Week 8 - 14 July ====
  +
Objectives :
  +
  +
==== Week 15 - 21 July ====
  +
Objectives :
  +
  +
==== Week 22 - 28 July (Second Evaluation evaluation) ====
  +
Objectives :
  +
  +
==== Week 29 July - 4 August ====
  +
Objectives :
  +
  +
==== Week 5 - 11 August ====
  +
  +
Objectives: Working on improving the Mə̀dʉ̂mbɑ̀ (byv) coverage
  +
  +
==== Week 12 - 18 August ====
  +
Objectives: TBD
  +
  +
==== Week 19 - 25 August ====
  +
Objectives : TBD

Latest revision as of 13:35, 5 August 2019

General Timetable[edit]

Variable over time but will be adjusted to provide at least 40 hours a week. Depending on mentors’ opinions, the timetable will be modified

A detailed timetable will be written each week (Monday morning) with the clear objectives and

Time Monday Tuesday Wednesday Thursday Friday Saturday Sunday
6 - 8 Working working
8 - 10 Working working
10 - 12 Working working
12 - 14
14 - 16
16 - 18 Working working
18 - 20 Working Working Working Working Working Working Working
20 - 23 Working Working Working Working Working Working working

Time is in GMT+1 Central Africa Time

[Comment] Monday will register my highest activity because of the political issue

Regular Activities[edit]

  • Reporting on work progress by writing new (or updating previous) wiki pages
  • Write articles for the byv-wiki

Log[edit]

Medumba progress
Date byv lexicon size Corpus size Coverage
12.06.2019 189 8674 ~0.37
20.06.2019 317 8674 ~0.39
05.07.2019 317 8674 ~0.56
10.07.2019 1186 6604 ~0.83
2019-07-21 1703 22627 ~65.21%
2019-07-25 1705 22637 ~69.19%
2019-07-25 17594 22624 ~77.77%
2019-08-05 27896 35035 ~79.62%
Medumba-French progress
Date byv-fra lexicon size Coverage WER, PER
12.06.2019 1592 ~0.10 Something
05.07.2019 1592 ~0.20 Something
10.07.2019 1592 ~0.35 Something


Community bonding[edit]

Week 13 - 19 May[edit]

Objectives :

  • Have 10000 words of byv-fra corpus
  • Sort words from corpus by frequency
  • Run the first test of the analyser and see what coverage do we achieve with 1800 entries.

Report : 1000 words in the corpus.
So the work has to be continued
Repo : Apertium-byv-fra

Week 20 - 25 May[edit]

Objectives :

  • Have 10000 words of byv-fra corpus
  • Sort words from corpus by frequency
  • Run the first test of the analyser and see what coverage do we achieve with 1800 entries.

Result: 2500 BYV entries

Week 26 May - 2 June[edit]

Objectives :

  • Continuation

Result: 6000 BYV words in the corpus

Week 3 - 9 June[edit]

Objectives :

Week 10 - 16 June[edit]

Objectives :

Week 17 - 23 June[edit]

Objectives :

Week 24 - 30 June (First evaluation)[edit]

Objectives: Fix the morphological analyser to recognise more words

Week 1 July - 7 July[edit]

Objectives : Make both dictionaries even so as to increase byv-fra coverage

Week 8 - 14 July[edit]

Objectives :

Week 15 - 21 July[edit]

Objectives :

Week 22 - 28 July (Second Evaluation evaluation)[edit]

Objectives :

Week 29 July - 4 August[edit]

Objectives :

Week 5 - 11 August[edit]

Objectives: Working on improving the Mə̀dʉ̂mbɑ̀ (byv) coverage

Week 12 - 18 August[edit]

Objectives: TBD

Week 19 - 25 August[edit]

Objectives : TBD