Difference between revisions of "User:Pmodi/GSOC 2020 proposal: Hindi-Punjabi/progress"

Revision as of 19:18, 2 June 2020

Progress on [1]

DONE - Added about 1400 adjective stems
DONE - Function words(cnj, det, prn, post, gen_endings), Coverage > 47%
DONE - Collected parallel texts to calculate WER,PER etc..
DONE - Added bidirectional dictionary(33k paradigms)
DONE - Fixed bidirectional translation i.e. pan->hin(gave close to human translation for small test set, even though similar transfer rules were copied)
DONE - Scraped all Wikipedia texts and made a combined frequency list.
DONE - Frequency lists using WikiExtractor on latest dump.

IN PROGRESS - Adding Adverbs.
IN PROGRESS - Fix inconsistencies with parallel texts.
IN PROGRESS - Practicing basic understanding of Persian script.
IN PROGRESS - Extracting stems and suffix/prefix patterns using the frequency lists(might not be so beneficial since Punajbi and Hindi share inflections for different word forms)

Week		Stems			Coverage			WER,PER		Progress
№	dates	hin	pan	hin-pan	hin	pan	hin-pan	hin→pan	pan→hin	Evaluation	Notes
1	May 1-24	-	-	-	-	47%	-	-	-	-	-

@@ Line 1: / Line 1: @@
 Progress on [https://wiki.apertium.org/wiki/User:Pmodi/GSOC_2020_proposal:_Hindi-Punjabi]
-==Current task(Community bonding Week 4)==
+==Current tasks(Week 1)==
-Fix some discrepancies due to postpositions(posttransfer) and add Adjectives, Adverbs.
+* Fix some discrepancies due to postpositions(posttransfer)
+* Add Adverbs.
+* Clean up parallel text and compute WER.
 ===DONE===
+* DONE - Added about 1400 adjective stems
 * DONE - Function words(cnj, det, prn, post, gen_endings), Coverage > 47%
 * DONE - Collected parallel texts to calculate WER,PER etc..
@@ Line 13: / Line 16: @@
 ===IN PROGRESS===
-* IN PROGRESS - Adding Adjectives(~1300 stems) and Adverbs.
+* IN PROGRESS - Adding Adverbs.
 * IN PROGRESS - Fix inconsistencies with parallel texts.
 * IN PROGRESS - Practicing basic understanding of Persian script.