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

From Apertium
Jump to navigation Jump to search
(32 intermediate revisions by the same user not shown)
Line 1: Line 1:
  +
==Current tasks(Week 5)==
Progress on [https://wiki.apertium.org/wiki/User:Pmodi/GSOC_2020_proposal:_Hindi-Punjabi]
 
  +
* Fix सब__prn for खुद
  +
* Fix determiners in Hindi (Add काफी to determiners)
  +
* Add post-positions to definitions - ਹਸਪਤਾਲੋਂ = ਹਸਪਤਾਲ ਤੋਂ.
  +
* What is the analysis for ਦੋਸਤੋਂ.
  +
* ਮੈਂ is the translation for मैंने and मैं. Add transfer rule and check if tagger correctly identifies which one is being picked.
  +
* Fix alternate spellings analyses..
  +
* कि v/s की punjabi ki can also be kya.
  +
* Fix gender for adj - ਬਹੁਤੀ
  +
* Complete manual analysis of bidix entries for adjectives and adverbs.
  +
* Add more verbs.
  +
* Run testvoc on Adjectives and Adverbs.
   
==Current tasks(Week 1)==
+
== Progress ==
  +
=== Progress table ===
* 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..
 
* 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===
 
* 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)
 
 
==TODO(Next week - Community Bonding Week 3)==
 
* Fix transfer rules for postpositions(fixing some issues).
 
* Start work on function words addition to dictionary.
 
 
==Literature(Apertium Wiki) Covered==
 
* DONE - Calculating Coverage.
 
* DONE - A long introduction on Transfer Rules.
 
* DONE - Transfer Rules examples
 
* DONE - Wikipedia Dumps.
 
* DONE - Generating Frequency lists.
 
* DONE - Building Dictionaries#Monolingual.
 
* DONE - Evaluation.
 
 
== Progress table ==
 
   
 
{|class=wikitable
 
{|class=wikitable
Line 69: Line 48:
 
! -
 
! -
 
! -
 
! -
  +
! Original coverage - 12.8%
! -
 
 
|-
 
|-
   
Line 75: Line 54:
 
! May 24-31
 
! May 24-31
 
! -
 
! -
! -
+
! +1400
 
! -
 
! -
 
! -
 
! -
Line 84: Line 63:
 
! -
 
! -
 
! WER, PER On a set of 25 sentences(612 words)
 
! WER, PER On a set of 25 sentences(612 words)
  +
|-
  +
  +
  +
! 3
  +
! June 1-7
  +
! -
  +
! +500
  +
! +250
  +
! -
  +
! 58%
  +
! -
  +
! 49.52%, 42.71%
  +
! 48.65%, 44.03%
  +
! -
  +
! WER, PER On a set of 50 sentences(1038 words)
  +
|-
  +
  +
! 4
  +
! June 8-14
  +
! +50
  +
! +1500
  +
! +1000
  +
! -
  +
! 63%
  +
! -
  +
! 41.36%, 35.82%
  +
! 41.47%, 37.03%
  +
! -
  +
! WER, PER On a set of 50 sentences(1038 words)
  +
|-
  +
  +
! 5
  +
! June 15-21
  +
! -
  +
! +50
  +
! +200
  +
! -
  +
! 66%
  +
! 52.8%
  +
! 41.36%, 35.82%
  +
! 41.47%, 37.03%
  +
! -
  +
! WER, PER On a set of 50 sentences(1038 words)
  +
|-
  +
  +
! 6
  +
! June 22-28
  +
! -
  +
! +350
  +
! +700
  +
! -
  +
! 70%
  +
! 59%
  +
! 39.76%, 34.22%
  +
! 40.03%, 36.23%
  +
! -
  +
! WER, PER On a set of 50 sentences(1038 words)
 
|}
 
|}
  +
  +
===DONE===
  +
* DONE - Bidix updates.
  +
* DONE - Fixed errors with postposition transfer.
  +
* DONE - Added proper nouns.
  +
* DONE - Added noun paradigms.
  +
* DONE - Added Adverbs.
  +
* 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===
  +
* IN PROGRESS - Adding Verbs.
  +
* IN PROGRESS - Fix inconsistencies with parallel texts.
  +
* IN PROGRESS - Practicing basic understanding of Persian script.
  +
  +
==TODO(Next week - Week 3)==
  +
* Add verbs and nouns.
  +
  +
==Literature(Apertium Wiki) Covered==
  +
* DONE - Calculating Coverage.
  +
* DONE - A long introduction on Transfer Rules.
  +
* DONE - Transfer Rules examples
  +
* DONE - Wikipedia Dumps.
  +
* DONE - Generating Frequency lists.
  +
* DONE - Building Dictionaries#Monolingual.
  +
* DONE - Evaluation.
  +
* DONE - Extract.
  +
* DONE - Monodix Basics
  +
* DONE - Improved Corpus Based Paradigm Matching.
  +
* DONE - Transliteration.
  +
* DONE - Workflow reference.
  +
* DONE - Tagger Tranining.
  +
* DONE - Modes introduction.
  +
* DONE - Apertium-viewer.

Revision as of 18:09, 1 July 2020

Current tasks(Week 5)

  • Fix सब__prn for खुद
  • Fix determiners in Hindi (Add काफी to determiners)
  • Add post-positions to definitions - ਹਸਪਤਾਲੋਂ = ਹਸਪਤਾਲ ਤੋਂ.
  • What is the analysis for ਦੋਸਤੋਂ.
  • ਮੈਂ is the translation for मैंने and मैं. Add transfer rule and check if tagger correctly identifies which one is being picked.
  • Fix alternate spellings analyses..
  • कि v/s की punjabi ki can also be kya.
  • Fix gender for adj - ਬਹੁਤੀ
  • Complete manual analysis of bidix entries for adjectives and adverbs.
  • Add more verbs.
  • Run testvoc on Adjectives and Adverbs.

Progress

Progress table

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% - - - - Original coverage - 12.8%
2 May 24-31 - +1400 - - 52% - 36.83%, 33.84% 40.03%, 36.93% - WER, PER On a set of 25 sentences(612 words)
3 June 1-7 - +500 +250 - 58% - 49.52%, 42.71% 48.65%, 44.03% - WER, PER On a set of 50 sentences(1038 words)
4 June 8-14 +50 +1500 +1000 - 63% - 41.36%, 35.82% 41.47%, 37.03% - WER, PER On a set of 50 sentences(1038 words)
5 June 15-21 - +50 +200 - 66% 52.8% 41.36%, 35.82% 41.47%, 37.03% - WER, PER On a set of 50 sentences(1038 words)
6 June 22-28 - +350 +700 - 70% 59% 39.76%, 34.22% 40.03%, 36.23% - WER, PER On a set of 50 sentences(1038 words)

DONE

  • DONE - Bidix updates.
  • DONE - Fixed errors with postposition transfer.
  • DONE - Added proper nouns.
  • DONE - Added noun paradigms.
  • DONE - Added Adverbs.
  • 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

  • IN PROGRESS - Adding Verbs.
  • IN PROGRESS - Fix inconsistencies with parallel texts.
  • IN PROGRESS - Practicing basic understanding of Persian script.

TODO(Next week - Week 3)

  • Add verbs and nouns.

Literature(Apertium Wiki) Covered

  • DONE - Calculating Coverage.
  • DONE - A long introduction on Transfer Rules.
  • DONE - Transfer Rules examples
  • DONE - Wikipedia Dumps.
  • DONE - Generating Frequency lists.
  • DONE - Building Dictionaries#Monolingual.
  • DONE - Evaluation.
  • DONE - Extract.
  • DONE - Monodix Basics
  • DONE - Improved Corpus Based Paradigm Matching.
  • DONE - Transliteration.
  • DONE - Workflow reference.
  • DONE - Tagger Tranining.
  • DONE - Modes introduction.
  • DONE - Apertium-viewer.