Difference between revisions of "Maltese and Arabic/Work plan"

Revision as of 06:30, 29 May 2012

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

Trimmed coverage means the coverage of both 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, in both translation directions.
Evaluation is taking $n$ words and performing an evaluation for post-edition word error rate (WER). The output for those $n$ words should be clean.

Week	Dates	Trimmed coverage	Testvoc	Evaluation	Notes
0	~~23/04—21/05~~	45%	`<sent>` `<cm>` `<ij>`	500 words	Preliminary evaluation. Translate the story total coverage and without diagnostics. Get a baseline WER. Aim to get the two mt verb scripts merged.
1	~~21/05—27/05~~	50%	`<num>` `<pr>`	-	Basic numerals, and prepositions should be testvoc clean. Maltese verb scripts merged.
2	28/05—03/06	53%	`<cnjcoo>` `<cnjadv>` `<cnjsub>`	-	Create ar verb script based on mt, add ar open-class words according to frequency
3	04/06—10/06	59%	`<adv>`	200 words	Continue adding open class words to ar (adding to bidix/mt as you go)
4	11/06—17/06	63%	`<prn>` `<det>`	-	Monodix completion; closed classes should be testvoc clean.
5	18/06—24/06	68%	`<adj>`	-	Bidix expansion; bidix adjectives should be testvoc clean.
6	25/06—01/07	70%	`<n>` `<np>`	500 words	Midterm evaluation. Bidix expansion, multiwords.
7	02/07—08/07	73%	-	-	Transfer
8	09/07—15/07	75%	-	-	Transfer, corpus testvoc
9	16/07—22/07	77%	-	200 words	Disambiguation, retrain tagger
10	23/07—29/07	80%	`<v>`	-	Testvoc
11	30/07—05/08	80%	-	-	Testvoc
12	06/08—12/08	80%	all categories clean	500 words	Final evaluation. Tidying up, releasing

@@ Line 12: / Line 12: @@
 | 0       || <s>23/04&mdash;21/05</s>  ||   45%            ||  {{tag|sent}} {{tag|cm}}  {{tag|ij}}  ||   500 words || '''Preliminary evaluation'''. Translate the story total coverage and without diagnostics. Get a baseline WER. Aim to get the two mt verb scripts merged.
 |-
-| 1       || 21/05&mdash;27/05  ||   50%            ||  {{tag|num}} {{tag|pr}} || -     || Basic numerals, and prepositions should be testvoc clean. Maltese verb scripts merged.
+| 1       || <s>21/05&mdash;27/05</s>  ||   50%            ||  {{tag|num}} {{tag|pr}} || -     || Basic numerals, and prepositions should be testvoc clean. Maltese verb scripts merged.
 |-
 | 2       || 28/05&mdash;03/06  ||   53%            ||  {{tag|cnjcoo}} {{tag|cnjadv}} {{tag|cnjsub}} || -     || Create ar verb script based on mt, add ar open-class words according to frequency