Difference between revisions of "User:Kamush/GSoC2021ProgresReport"

From Apertium
Jump to navigation Jump to search
 
(33 intermediate revisions by the same user not shown)
Line 17: Line 17:
May 17-June 5
May 17-June 5
|
|
* Installing Apertium
* Installed Apertium
* Initialize kaz-uzb pair
* Initialize kaz-uzb pair
* Collect data in both languages
* Collect data in both languages
| style = "text-align: center;" | 426
| -
(+426)
| -
| style = "text-align: center;" | 43.80 %
| -
| -
| -
| -
|
|
* Installing Apertium and necessary tools;
* Installed Apertium and necessary tools;
* Cloned Apertium-kaz and apertium-uzb, initialized the kaz-uzb pair
* Send the first PR that can translate a small sample text;
* Translated a small sample text;
* Extract Uzbek and Kazakh wiki corpus;
* Collect Uzbek and Kazakh web(non-wiki) corpus;
* Extracted Uzbek and Kazakh wiki corpus;
* Collect Kazakh-Uzbek dictionary and parallel corpora;
* Collected Kazakh-Uzbek dictionary and parallel corpora;
|-
|-
|Week 1
|Week 1
June 6-12
June 6-12
|Make Uzbek better
|Make Uzbek better
| style = "text-align: center;" | 2220
| -
(+1794)
| -
| style = "text-align: center;" | 52.11 %
| -
| -
| -
| -
|
|
* Go through all Uzbek stems in uzb.lexc;
* Went through all Uzbek and Kazakh stems;
* Initialized the pair with apertium-recursive;
* Clean(deduplicate) and correct uzb stems;
* Collected dictionaries from other pairs for crossdic;
* Improve Uzbek lexicon;
* Obtained crossdic results from two ways.
|-
|-
|Week 2
|Week 2
June 13-19
June 13-19
| Expand bilingual dictionary
| Expand bilingual dictionary
| style = "text-align: center;" | 5262
| -
(+3042)
| -
| style = "text-align: center;" | 77.03 %
| -
| 74.77% / 67.57%
| -
| 64.23% / 54.37%
|
|
* Start adding bilingual dictionary elements;
* Started adding bilingual dictionary elements;
|-
|-
|Week 3
|Week 3
June 20-26
June 20-26
| More on .dix and .lrx
| More on .dix and .lrx
| style = "text-align: center;" | 8543
| -
(+3281)
| -
| style = "text-align: center;" | 81.55 %
| -
| 74.77% / 67.57%
| -
| 64.23% / 54.37%
|
|
* Expand bilingual dictionary;
* Expanded bilingual dictionary;
* Lexical selection rules;
* Started sample Lexical selection rules;
|-
|-
|Week 4
|Week 4
June 27-July 3
June 27-July 3
|Focus on transfer rules
|Focus on transfer rules
| style = "text-align: center;" | 9432
| -
(+889)
| -
| style = "text-align: center;" | 81.85 %
| -
| 74.77% / 67.57%
| -
| 64.23% / 54.37%
|
|
* Expand bilingual dictionary;
* Expanded bilingual dictionary more;
* Lexical selection rules;
|-
|-
|Week 5
|Week 5
July 4-10
July 4-10
|Test translator and expand more
|Test translator and expand more
| style = "text-align: center;" | 11008
| -
(+1576)
| -
| style = "text-align: center;" | 82.81%
| -
| 74.77% / 67.57%
| -
| 64.23% / 54.37%
|
|
* Expanded bilingual dictionary;
* Test the kaz-uzb translator;
* Collected texts for lexical selection rules, tried a small script;
* Expand the Uzbek lexicon with missing words;
* Translated a Big Kazkh text into Uzbek for better WER/PER calculation.
* Expand bilingual dictionary;
* Expand lexical selection rules;
|-
|-
|Week 6
|Week 6
July 11-17
July 11-17
|Focus more on transfer rules
|Focus more on transfer rules
| style = "text-align: center;" | +191
| -
| style = "text-align: center;" | 84.46 %
| -
| 71.83% / 63.52%
| -
| 67.24% / 60.31%
| -
|
|
* Addeed more stems to the bidix to reach 85% coverage
* Work more on transfer rules;
* Added 1500+ Lexical Selection Rules to kaz-uzb.lrx for ambiguous translations
* More bilingual dictionary;
* Added 1200+ Lexical Selection Rules to uzb-kaz.lrx for ambiguous translations
* More lexical section rules;
* Prepared 200 sentences of parallel corpora.
*
|-
|-
|Week 7
|Week 7
July 18-24
July 18-24
|Test the kaz-uzb translator
|Test the kaz-uzb translator
| style = "text-align: center;" | +219
| -
| style = "text-align: center;" | 84.58 %
| -
| 69.21% / 60.69%
| -
| 67.10% / 59.89%
| -
|
|
* Test the kaz-uzb translator;
* Started the transfer rules
* Some more bidix
* Extend the Uzbek lexicon with missing words;
* Some Lexical selection rules
* Extend the Kazakh lexicon with missing words;
* Extend bilingual dictionary;
* Add more lexical selection rules;
|-
|-
|Week 8
|Week 8
July 25-31
July 25-31
|Focus on transfer rules
|Focus on transfer rules
| style = "text-align: center;" | +500
| -
| style = "text-align: center;" | 85.17 %
| -
| 69.21% / 60.69%
| -
| 67.10% / 59.89%
| -
|
|
* Some additions to apertium-kaz & apertium-uzb
* Add words, rules;
* Work on transfer rules;
* Some transfer rules
* Some more lexical selection rules & bidix
* Start the testvoc;
|-
|-
|Week 9
|Week 9
August 1-7
August 1-7
|Focus on testvoc
|Focus on testvoc
| style = "text-align: center;" | +1000
| -
| style = "text-align: center;" | 86.02 %
| -
| 71.37% / 64.81%
| -
| 61.93% / 56.05%
| -
|
|
* More frequent words added to the dictionary
* Add words, rules;
* Transfer rules kaz-uzb;
* Testvoc kaz-uzb
|-
|-
|Week 10
|Week 10
August 8-14
August 8-14
|Finalize work
|Finalize work
| style = "text-align: center;" | +400
| -
| style = "text-align: center;" | 86.02 %
| -
| 71.37% / 64.81%
| -
| 61.93% / 56.05%
| -
|
|
* More post-editing done
* Test the kaz-uzb translator;
* Check the transfer rules;
* Check the testvoc;
* Write the final report;
|-
|-
|}
|}

== TODO ==
* More transfer rules
* Testvoc

== ONGOING ==

* Transfer rules
* Some lexical selection rules
* Collecting more bidix
** Adding only most-frequent words from kazakh wiki hitparade until 85% coverage is reached

== DONE (+Notes & Comments) ==
* Made a script to calculate WER for each line of the kaz-uzb.txt file to see what sentences are causing the most problems.
* Translating big Kaz text into Uzb
** Aside from those small texts obtained from parallel corpora
** For better WER/PER calculation
** For checking transfer rules
** Started with readily available small JaM Story
*** Azmat and Oygul story in our case
*** Added 47 sentences from that.
** Chose Nur-Sultan(capital city) article of Kazakh Wiki for that.
*** Split the article into sentences, translated into uzb manually.
*** Added 112 sentences out of Nur-Sultan text.
** Used QED parallel corpus form internet.
*** Manually selected sentences and corrected their translations.
*** Added 90 sentences from this.
** Made 250 sentences in total, stopping this here.
* Tried finding parallel corpora:
** ''https://opus.nlpl.eu/''
*** KDE4: Not good: ''https://opus.nlpl.eu/KDE4/v2/kk-uz_sample.html''
*** MozillaI10: Nope
*** '''QED''':
**** kk-uz.tmx file
**** Good, Gonna use this, but needs manual selection and corrections on translations.
*** TED: the same file with QED.
*** The rest is also not good, just one-word translation mostly.
* Lexical selection rules for kaz-uzb
** Created a script to analyse bidix and find ambiguous stems.
** Created a script that generates lexical selection rules from manually chosen stems
** Rules added in kaz-uzb.lrx for 1565 words.
** Rules added in uzb-kaz.lrx for 1295 words.
* '''Apertium-dixtools:'''
** ''https://wiki.apertium.org/wiki/Apertium-dixtools''
** Fixing bidix(deduplicating, removing empty lines):
apertium-dixtools fix apertium-kaz-uzb.kaz-uzb.dix apertium-kaz-uzb.kaz-uzb.dix.fixed
** Sorting bidix(aligning too):
apertium-dixtools sort -alignBidix -ignorecase apertium-kaz-uzb.uz-uzb.dix apertium-kaz-uzb.kaz-uzb.dix.sorted
* Sorting+Deduplicating the bidix for future purposes:
** Bidix count before deduplication: 11008
** Fixing the bidix:
*** Removed 1501 entries in section main
** Bidix count after deduplication: 9507
** Sorted+Regrouped the dix.
* Made a script to calculate DixCount, Coverage, WER/PER at once
* '''Calculating WER/PER:'''
** Apertium-eval-translator:
*** ''https://github.com/apertium/apertium-eval-translator''
$ cat kaz-big.txt | apertium -d ../ kaz-uzb > kaz-uzb.txt
$ cat uzb-big.txt | apertium -d ../ uzb-kaz > uzb-kaz.txt
$ apertium-eval-translator -ref uzb-big.txt -test kaz-uzb.txt
$ apertium-eval-translator -ref kaz-big.txt -test uzb-kaz.txt
** '''Parallel text:'''
*** JaM Story:
*** “Azamat va Oygul” in our case;
*** kaz-uzb/texts/[kaz|uzb].txt
** Astana article from Kazakh Wiki
* '''Calculated dix Coverage:'''
** (kaz-uzb/texts): bash ../../coverage-ltproc-new.sh ../docs/kaz-wiki.txt ../kaz-uzb.automorf.bin
** coverage: 26752095 / 32305875 (~0.82808761564266561423)
** remaining unknown forms: 5553780
** kaz-wiki.txt Sun Jul 11 11:55:25 CEST 2021
* '''Counting Dix elements:'''
** Apertium-Eval: dixcounter.py:
python3 ../dixcounter.py apertium-kaz-uzb.kaz-uzb.dix

** July 09: 11008 dix elements before deduplication.
* Translating kaz-uig.dix into kaz-uzb
* Translating kaz-kaa.dix into kaz-uzb.dix
** Removing those that were already done by crossdic
** Changing karakalpak translation into uzbek one by looking at both kazakh and karakalpak words
* Translating kaz-tur.dix into kaz-uzb.dix
** Removing those that were already done by crossdic
** Changing turkish translation into uzbek one by looking at both kazakh and turkish words
** Added 3200 more words from this.
* '''Extract Kazakh wikipedia:'''
** Kazakh wiki date: 01.05.2021
*** https://dumps.wikimedia.org/kkwiki/20210501/
** Apertium-tools: WikiExtractor:
*** Wiki: ''https://wiki.apertium.org/wiki/WikiExtractor''
*** Code: ''https://svn.code.sf.net/p/apertium/svn/trunk/apertium-tools/WikiExtractor.py''
python3 WikiExtractor.py --infn kkwiki-20210501-pages-articles-multistream.xml.bz2

** Saved resulting corpus in docs/kaz-wiki.txt, ~24M tokens
* '''Big Crossdix action:'''
** Crossing dictionaries: kaz-kaa and kaa-uzb
** Crossing dictionaries: kaz-tur and tur-uzb
** Merge the obtained crossdix outputs from two
** Sort the merged file, removing duplicates
** Align the result for better visibility
** Manually check every translation, remove if bad, correct/add if necessary
** Added 5000+ words from this.
* Start collecting the kaz-uzb bilingual dictionary
* '''Convert the pair to apertium-recursive'''
** Done!!!, but I had to remove the entire bilingual repo and recreate it from scratch.
* Write some lexical selection rules in kaz-uzb.
** Wiki: ''https://wiki.apertium.org/wiki/How_to_get_started_with_lexical_selection_rules''
** Definitely needed samples:
*** The closest sample is apertium-kaz-tur
*** ''https://github.com/apertium/apertium-kaz-tur''
* '''Translate small text (James & Mary story)'''
** Source: https://github.com/taruen/apertiumpp/tree/master/data4apertium/corpora/jam
** James&Mary story was downloaded from the source.
** apertium-kaz-uzb/texts/
** Updated as Azamat & Oygul story
* Translating a text file:
cat texts/kaz.txt | apertium -d . -f line kaz-uzb
* Translation of a sentence:
echo 'Сәлем Әлем' | apertium -d . kaz-uzb
* Bootstrapping a new language pair apertium-kaz-uzb
** Installed Apertium-init from pip
*** Had a problem, solved it (tanks to @popcorndude).
** Downloaded apertium-init.py
*** Did not work
python3 apertium-init.py kaz-uzb --analyser=hfst --no-prob1 --no-prob2
cd apertium-kaz-uzb
./autogen.sh --with-lang1=../apertium-kaz --with-lang2=../apertium-uzb & make
** I had to convert it to apertium-recursive, so further flags to be added:
*** ''-t rtx''
* Final initialization command:
python3 apertium-init.py kaz-uzb --analyser=hfst --no-prob1 --no-prob2 -t rtx
* '''Forked(&Installed) necessary repos on GitHub:'''
** '''''Apertium-kaz'''''
*** ''git clone git@github.com:kamush901/apertium-kaz.git''
*** Works well
** '''''Apertium-uzb'''''
*** ''git@github.com:kamush901/apertium-uzb.git''
*** Works well
* '''Installed Apertium and necessary tools:'''
** Installed Apertium core using packaging
wget https://apertium.projectjj.com/apt/install-nightly.sh -O - | sudo bash
sudo apt-get -f install apertium-all-dev

Latest revision as of 11:51, 31 August 2021

Progress Report[edit]

Time Period Goal Bidix Coverage WER,PER Details/Comments
kaz-uzb kaz-uzb kaz-uzb uzb-kaz
Community Bonding Period

May 17-June 5

  • Installed Apertium
  • Initialize kaz-uzb pair
  • Collect data in both languages
 426

(+426)

43.80 % - -
  • Installed Apertium and necessary tools;
  • Cloned Apertium-kaz and apertium-uzb, initialized the kaz-uzb pair
  • Translated a small sample text;
  • Extracted Uzbek and Kazakh wiki corpus;
  • Collected Kazakh-Uzbek dictionary and parallel corpora;
Week 1

June 6-12

Make Uzbek better 2220

(+1794)

52.11 % - -
  • Went through all Uzbek and Kazakh stems;
  • Initialized the pair with apertium-recursive;
  • Collected dictionaries from other pairs for crossdic;
  • Obtained crossdic results from two ways.
Week 2

June 13-19

Expand bilingual dictionary 5262

(+3042)

77.03 % 74.77% / 67.57% 64.23% / 54.37%
  • Started adding bilingual dictionary elements;
Week 3

June 20-26

More on .dix and .lrx 8543

(+3281)

81.55 % 74.77% / 67.57% 64.23% / 54.37%
  • Expanded bilingual dictionary;
  • Started sample Lexical selection rules;
Week 4

June 27-July 3

Focus on transfer rules 9432

(+889)

81.85 % 74.77% / 67.57% 64.23% / 54.37%
  • Expanded bilingual dictionary more;
Week 5

July 4-10

Test translator and expand more 11008

(+1576)

82.81% 74.77% / 67.57% 64.23% / 54.37%
  • Expanded bilingual dictionary;
  • Collected texts for lexical selection rules, tried a small script;
  • Translated a Big Kazkh text into Uzbek for better WER/PER calculation.
Week 6

July 11-17

Focus more on transfer rules +191 84.46 % 71.83% / 63.52% 67.24% / 60.31%
  • Addeed more stems to the bidix to reach 85% coverage
  • Added 1500+ Lexical Selection Rules to kaz-uzb.lrx for ambiguous translations
  • Added 1200+ Lexical Selection Rules to uzb-kaz.lrx for ambiguous translations
  • Prepared 200 sentences of parallel corpora.
Week 7

July 18-24

Test the kaz-uzb translator +219 84.58 % 69.21% / 60.69% 67.10% / 59.89%
  • Started the transfer rules
  • Some more bidix
  • Some Lexical selection rules
Week 8

July 25-31

Focus on transfer rules +500 85.17 % 69.21% / 60.69% 67.10% / 59.89%
  • Some additions to apertium-kaz & apertium-uzb
  • Some transfer rules
  • Some more lexical selection rules & bidix
Week 9

August 1-7

Focus on testvoc +1000 86.02 % 71.37% / 64.81% 61.93% / 56.05%
  • More frequent words added to the dictionary
Week 10

August 8-14

Finalize work +400 86.02 % 71.37% / 64.81% 61.93% / 56.05%
  • More post-editing done

TODO[edit]

  • More transfer rules
  • Testvoc

ONGOING[edit]

  • Transfer rules
  • Some lexical selection rules
  • Collecting more bidix
    • Adding only most-frequent words from kazakh wiki hitparade until 85% coverage is reached

DONE (+Notes & Comments)[edit]

  • Made a script to calculate WER for each line of the kaz-uzb.txt file to see what sentences are causing the most problems.
  • Translating big Kaz text into Uzb
    • Aside from those small texts obtained from parallel corpora
    • For better WER/PER calculation
    • For checking transfer rules
    • Started with readily available small JaM Story
      • Azmat and Oygul story in our case
      • Added 47 sentences from that.
    • Chose Nur-Sultan(capital city) article of Kazakh Wiki for that.
      • Split the article into sentences, translated into uzb manually.
      • Added 112 sentences out of Nur-Sultan text.
    • Used QED parallel corpus form internet.
      • Manually selected sentences and corrected their translations.
      • Added 90 sentences from this.
    • Made 250 sentences in total, stopping this here.
  • Tried finding parallel corpora:
  • Lexical selection rules for kaz-uzb
    • Created a script to analyse bidix and find ambiguous stems.
    • Created a script that generates lexical selection rules from manually chosen stems
    • Rules added in kaz-uzb.lrx for 1565 words.
    • Rules added in uzb-kaz.lrx for 1295 words.
  • Apertium-dixtools: 
   apertium-dixtools fix apertium-kaz-uzb.kaz-uzb.dix apertium-kaz-uzb.kaz-uzb.dix.fixed
    • Sorting bidix(aligning too):
   apertium-dixtools sort -alignBidix -ignorecase apertium-kaz-uzb.uz-uzb.dix apertium-kaz-uzb.kaz-uzb.dix.sorted
  • Sorting+Deduplicating the bidix for future purposes:
    • Bidix count before deduplication: 11008
    • Fixing the bidix:
      • Removed 1501 entries in section main
    • Bidix count after deduplication: 9507
    • Sorted+Regrouped the dix.
  • Made a script to calculate DixCount, Coverage, WER/PER at once
  • Calculating WER/PER: 
   $ cat kaz-big.txt | apertium -d ../ kaz-uzb > kaz-uzb.txt
   $ cat uzb-big.txt | apertium -d ../ uzb-kaz > uzb-kaz.txt
   $ apertium-eval-translator -ref uzb-big.txt -test kaz-uzb.txt
   $ apertium-eval-translator -ref kaz-big.txt -test uzb-kaz.txt
    • Parallel text:
      • JaM Story:
      • “Azamat va Oygul” in our case;
      • kaz-uzb/texts/[kaz|uzb].txt
    • Astana article from Kazakh Wiki
  • Calculated dix Coverage:
    • (kaz-uzb/texts): bash ../../coverage-ltproc-new.sh ../docs/kaz-wiki.txt ../kaz-uzb.automorf.bin
    • coverage: 26752095 / 32305875 (~0.82808761564266561423)
    • remaining unknown forms: 5553780
    • kaz-wiki.txt Sun Jul 11 11:55:25 CEST 2021
  • Counting Dix elements:
    • Apertium-Eval: dixcounter.py:
   python3 ../dixcounter.py apertium-kaz-uzb.kaz-uzb.dix

   python3 WikiExtractor.py --infn kkwiki-20210501-pages-articles-multistream.xml.bz2
    • Saved resulting corpus in docs/kaz-wiki.txt, ~24M tokens
  • Big Crossdix action:
    • Crossing dictionaries: kaz-kaa and kaa-uzb
    • Crossing dictionaries: kaz-tur and tur-uzb
    • Merge the obtained crossdix outputs from two
    • Sort the merged file, removing duplicates
    • Align the result for better visibility
    • Manually check every translation, remove if bad, correct/add if necessary
    • Added 5000+ words from this.
  • Start collecting the kaz-uzb bilingual dictionary
  • Convert the pair to apertium-recursive
    • Done!!!, but I had to remove the entire bilingual repo and recreate it from scratch.
  • Write some lexical selection rules in kaz-uzb.
  • Translate small text (James & Mary story)
  • Translating a text file:
   cat texts/kaz.txt | apertium -d . -f line kaz-uzb
  • Translation of a sentence:
   echo 'Сәлем Әлем' | apertium -d . kaz-uzb
  • Bootstrapping a new language pair apertium-kaz-uzb
    • Installed Apertium-init from pip
      • Had a problem, solved it (tanks to @popcorndude).
    • Downloaded apertium-init.py
      • Did not work
   python3 apertium-init.py kaz-uzb --analyser=hfst --no-prob1 --no-prob2
   cd apertium-kaz-uzb
   ./autogen.sh --with-lang1=../apertium-kaz --with-lang2=../apertium-uzb & make
    • I had to convert it to apertium-recursive, so further flags to be added:
      • -t rtx
  • Final initialization command:
   python3 apertium-init.py kaz-uzb --analyser=hfst --no-prob1 --no-prob2 -t rtx
  • Forked(&Installed) necessary repos on GitHub:
    • Apertium-kaz
      • git clone git@github.com:kamush901/apertium-kaz.git
      • Works well
    • Apertium-uzb
      • git@github.com:kamush901/apertium-uzb.git
      • Works well
  • Installed Apertium and necessary tools:
    • Installed Apertium core using packaging
   wget https://apertium.projectjj.com/apt/install-nightly.sh -O - | sudo bash
   sudo apt-get -f install apertium-all-dev
Retrieved from "https://wiki.apertium.org/w/index.php?title=User:Kamush/GSoC2021ProgresReport&oldid=73734"