Turkic-Turkic translator

From Apertium
Jump to navigation Jump to search

Contents


Work plan

This is a general workplan for development efforts for Turkic--Turkic prototype translators. Suitable for use in the Google Summer of Code.

  • Trimmed coverage means the coverage of the morphological analysers after being trimmed according to the bilingual dictionary of the pair, that is, only containing stems which are also in the bilingual dictionary.
  • Testvoc for a category means that the category is testvoc clean.
  • Evaluation is taking words and performing an evaluation for post-edition word error rate (WER).
Week Dates Trimmed coverage Testvoc Evaluation Notes
0 23/04—21/05 45% - 500 words Translate the story without diagnostics. Get a baseline WER. Work on disambiguation.
1 21/05—27/05 50% <num> -
2 28/05—03/06 53% <cnjcoo> <cnjadv> <cnjsub> <postadv> <post> -
3 04/06—10/06 59% <adv> 200 words Work on disambiguation.
4 11/06—17/06 63% <prn> <det> -
5 18/06—24/06 68% <adj> <np> -
6 25/06—01/07 70% <n> 500 words Midterm evaluation. Work on disambiguation.
7 02/07—08/07 73% - -
8 09/07—15/07 75% - -
9 16/07—22/07 77% - 200 words Work on disambiguation.
10 23/07—29/07 80% <v> -
11 30/07—05/08 80% - 500 words Work on disambiguation.
12 06/08—12/08 80% all categories clean - Tidying up, releasing