Difference between revisions of "Indonesian and Malaysian/Work plan"

From Apertium
Jump to navigation Jump to search
Line 1: Line 1:
 
This is a workplan for development efforts for the [[Indonesian and Malaysian]] translator in [[Google Summer of Code]] 2012.
 
This is a workplan for development efforts for the [[Indonesian and Malaysian]] translator in [[Google Summer of Code]] 2012.
  +
  +
==Work plan==
   
 
{|class=wikitable
 
{|class=wikitable

Revision as of 11:49, 17 July 2012

This is a workplan for development efforts for the Indonesian and Malaysian translator in Google Summer of Code 2012.

Work plan

Week Dates Main activities Coverage reached (wp) Trimmed coverage reached (wp) Testvoc clean Evaluation WER reached
0 23/04—21/05 Translating the story to get a baseline WER. 500 words 4.68% (id->ms)
1 21/05—27/05 Working on Indonesian analyzer/generator.
2 28/05—03/06 Working on Indonesian analyzer/generator.
Translating Malaysian wikipedia articles to Indonesian to get a parallel corpus.
Bilingual dictionaries will be extracted from the corpus.
72.9%, 29.9%
3 04/06—10/06 Translating Malaysian wikipedia articles to Indonesian.
Working on Malaysian analyzer/generator.
74.9%, 46.4%
4 11/06—17/06 Working on Malaysian analyzer/generator and bidix. 75.6%, 72.9%
5 18/06—24/06 Working on Malaysian analyzer/generator and bidix. 80.1%, 77.5% 300 words 2.97% (ms->id)
6 25/06—01/07 Working on bidix. 80.1%, - 73.3%, - <ij> <cnjcoo> <cnjsub> <cnjadv> <det> <pr> <num> <prn> <np> <adv>
7 02/07—08/07 Working on bidix. 80.3%, 77.1% 76.5%, 74.6% 500 words 24.34% (ms->id)
8 09/07—15/07 Parallel corpus development.
9 16/07—22/07 Working on bidix.

Ideas for getting Indonesian-Malaysian bilingual dictionaries

  1. Filtering the Indonesian lemma list. For each lemma, check whether they are also valid Malaysian words.
  2. Interlanguage wiki links.
  3. Extracting bilingual dictionaries from parallel corpus.

Todo list

  1. Convert the Malaysian dictionary to Apertium format
  2. Create a script to get Indonesian word list
  3. Adding missing words from the story
  4. Adding conjunctives and interjections
  5. Assigning correct parameter which will be reduplicated, for verbs with meN- (id)
  6. Passive form for verbs with meN- (id) (Done: V -> V no suffix, no suffix + -kan; N -> V -kan)
  7. ter-, se-, peN-an, per-an
  8. Alternative POS for each word
  9. diper-, ber-an, ber-kan
  10. Check from the inflected and derived form, whether the lemma has been added as a separate entry
  11. ke-an variations -> better tag naming

See also

External links