Difference between revisions of "User:Elmurod1202/GSoC2020Progress"

From Apertium
Jump to navigation Jump to search
Line 7: Line 7:
 
!colspan="2"|Stems
 
!colspan="2"|Stems
 
!colspan="2"|Tur-Uzb
 
!colspan="2"|Tur-Uzb
!colspan="2"|Uzb-Tur
 
 
!colspan="2"|Naïve Coverage
 
!colspan="2"|Naïve Coverage
 
!colspan="2"|Progress
 
!colspan="2"|Progress
Line 15: Line 14:
 
! uzb
 
! uzb
 
! tur-uzb
 
! tur-uzb
! WER
 
! PER
 
 
! WER
 
! WER
 
! PER
 
! PER
Line 27: Line 24:
 
| May 4 - May 31
 
| May 4 - May 31
 
| 34375
 
| 34375
| 4359
+
| 2412
 
| 90.80 %
 
| 90.80 %
 
| 81.60 %
 
| 81.60 %
| 97.01 %
 
| 92.36 %
 
 
| 89.57 %
 
| 89.57 %
 
| 72.14 %
 
| 72.14 %
 
|Initial evaluation
 
|Initial evaluation
  +
| As of the end of May
|
 
 
|-
 
|-
 
| 1
 
| 1
Line 52: Line 47:
 
| June 29 - July 5
 
| June 29 - July 5
 
| 34373
 
| 34373
| 4360
+
| 2445
 
| 84.45 %
|
 
 
| 76.80 %
|
 
  +
| 90.23 %
|
 
|
 
|
 
 
| 72.14 %
 
| 72.14 %
  +
| First Evaluations
  +
| End of June - ~July 3
 
|-
 
|-
 
| 6
 
| 6
Line 71: Line 66:
 
| 9
 
| 9
 
| July 27 - Aug 2
 
| July 27 - Aug 2
  +
| 34424
  +
| 4191
  +
| 78.70 %
  +
| 68.34 %
  +
| 90.23 %
 
|
  +
| Second Evaluations
  +
| As of July 31 - Aug 1
 
|-
 
|-
 
| 10
 
| 10

Revision as of 16:21, 1 August 2020

The original proposal can be seen here

Status table

Week Stems Tur-Uzb Naïve Coverage Progress
Dates uzb tur-uzb WER PER uzb tur-uzb Evaluation Notes
0 May 4 - May 31 34375 2412 90.80 % 81.60 % 89.57 % 72.14 % Initial evaluation As of the end of May
1 June 1 - June 7
2 May 8 - June 14
3 June 15 - June 21
4 June 22 - June 28
5 June 29 - July 5 34373 2445 84.45 % 76.80 % 90.23 % 72.14 % First Evaluations End of June - ~July 3
6 July 6 - July 12
7 July 13 - July 19
8 July 20 - July 26
9 July 27 - Aug 2 34424 4191 78.70 % 68.34 % 90.23 % Second Evaluations As of July 31 - Aug 1
10 July 3 - Aug 9
11 Aug 10 - Aug 16
12 Aug 17 - Aug 23

To Do

Week 1-4

  • Introducing apertium-separable to the tur-uzb pair
  • Adding more stems to bilingual dictionary;
  • Transfer rules refactoring;
  • Increasing WER coverage;
  • Running tests
  • Updating documentation
  • Preparing for the first evaluation

Ongoing

  • Calculating initial naive coverage of monolingual apertium-uzb;
  • Calculating initial naive coverage of bilingual apertium-tur-uzb;

Done

Community bonding period (May 4 - June 1):

  • Getting closer with Apertium tools and community
  • Finding out the current state of Uzbek language
  • Finding out the availability of Uzbek resources
  • Learning more about the HFST
  • Doing coding challenge
  • Begin interacting with Apertium's core system

Notes