https://wiki.apertium.org/w/index.php?action=history&feed=atom&title=User%3AEden%2FGSOC2020_Swahili-LingalaUser:Eden/GSOC2020 Swahili-Lingala - Revision history2026-04-09T14:00:55ZRevision history for this page on the wikiMediaWiki 1.34.1https://wiki.apertium.org/w/index.php?title=User:Eden/GSOC2020_Swahili-Lingala&diff=72236&oldid=prevEden: Created page with "== Goal == Create a usable ‘Swahili-Lingala’ language pair. <br/> == Swahili and Lingala resources == Here is a list of ''open'' and ''public domain'' resources(dictionar..."2020-05-19T05:03:52Z<p>Created page with "== Goal == Create a usable ‘Swahili-Lingala’ language pair. <br/> == Swahili and Lingala resources == Here is a list of ''open'' and ''public domain'' resources(dictionar..."</p>
<p><b>New page</b></p><div>== Goal ==<br />
Create a usable ‘Swahili-Lingala’ language pair. <br/><br />
<br />
== Swahili and Lingala resources ==<br />
Here is a list of ''open'' and ''public domain'' resources(dictionaries, grammar books, texts, etc) for Swahili:<br/><br />
<br />
*Corpus/frequency list/bigram<br />
- [https://github.com/thefreezer/apertium-swa/blob/master/dev/wikipedia_corpus.txt ~7m word corpus](needs a little bit more work) <br/><br />
- [http://crubadan.org/writingsystems An Crúbadán] <br /><br />
*Dictionary<br />
- [https://kamusi.org/swahili-english-wordlist-2008 Swa-Eng] and [https://kamusi.org/english-swahili-wordlist-2008 Eng-Swa]<br/><br />
- [https://archive.org/details/swahilienglishdi00mada/page/n15/mode/2up Madan A.C.,1846], [https://archive.org/details/englishswahilid00madagoog/page/n13/mode/2up Madan A. C.,1902][https://archive.org/details/Swahili-englishDictionary/mode/2up Charles, W. R.]<br/><br />
- [https://github.com/freedict/fd-dictionaries/tree/master/swh-eng Freedict] <br/><br />
*Grammar rules<br />
- [https://en.wikipedia.org/wiki/Swahili_grammar Wikipedia's Grammar Rules]<br/><br />
- [https://archive.org/details/swahiligrammarvo00burtiala/page/96/mode/2up Burt, A. E,1910] <br/><br />
- [https://archive.org/details/ERIC_ED012888/page/n123/mode/2up Follome]<br/><br />
- [https://archive.org/details/ERIC_ED012888/page/n123/mode/2up Steerie, Edward]<br/><br />
*Other<br />
- [http://www.language-archives.org/language/swh Language Archive] <br/><br />
- [https://wals.info/languoid/lect/wals_code_swa WALS] <br/><br />
<br />
== Work plan ==<br />
Community bonding period(May 4-June 1)<br />
- See [[User:Eden/GSoC_progress]]<br />
<br />
Week 1(June 1-7): <br />
- adding nouns(from frequency list) in the lin transducer<br />
- Add nouns (from frequency list) in the swa transducer<br />
- Work on vowels<br />
- Constraint grammar for nouns<br />
- Add verbs<br />
<br />
Week 2(June 8-14):<br />
- adding pronouns and adjectives in the swa transducer <br />
- Continue work on verbs<br />
- Reference: kaz and lin transducers<br />
- Add prepositions and pronouns, conjunctions<br />
- Work on numerals<br />
- CG for all the above<br />
<br />
Week 3(June 15-21): <br />
- Regression testing<br />
- Test and polish transducer(work on bi-grams)<br />
- Finish adding adverbs, conjunctions, prepositions, etc<br />
- Start work on bilingual dictionary<br />
<br />
Week 4(June 22-28): <br />
- Add nouns and adjectives in bidix<br />
- Transfer rules for nouns and adjectives(both directions)<br />
- Disambiguation rules<br />
<br />
* '''Deliverable #1(June 29): Advanced Swahili transducer(>10k entries) with basic bilingual dictionary''' <br />
<br />
Week 5(June 29-July 5): <br />
- Continue work on bidix: add nouns and verbs <br />
- Focus on verbs<br />
- Transfer rules from eng-lin, kaz-eng, and eng-fre<br />
- Transfer rules for verbs in both directions<br />
<br />
Week 6(July 6-12): <br />
- Add pronouns and transfer rules for them<br />
- Add adverbs<br />
- Wok on compound Swahili words<br />
- Transfer rules for pronouns, adverbs and compound nouns(both directions)<br />
<br />
Week 7(July 13-19): <br />
- Goal: well defined macros for verbs and pronouns<br />
- WER < 35% on 500 word story<br />
- add/polish rules for concordance between verbs and pronouns<br />
<br />
Week 8(July 20-26): <br />
- Continue work on transfer rules<br />
- Work on disambiguation rules<br />
- Lots of testing and improvements<br />
- WER < 30% in both directions on a 1,000-word story<br />
<br />
* '''Deliverable #2(July 3): Advanced bilingual dictionary(~15,000 words) and transfer rules''' ...<br />
<br />
Week 9(July 27-August 2) :<br />
- Continue work on disambiguation(both directions)<br />
- Testvoc and improvements<br />
- Filling bidix<br />
<br />
Week 10(August 3-9):<br />
- Work on transfer rules<br />
- goal is WER ~30% on a story greater > 1000 words<br />
<br />
Week 11(August 10-16):<br />
- Continue work on transfer rules and testing<br />
- Wikipedia article translations<br />
- Continue filling bidix<br />
<br />
Week 12(August 17-23):<br />
- Continue filling bidix with miscellaneous words<br />
- Detailed analysis of work completed(wiki)<br />
- (if work done well, start working on new pairs)<br />
- Evaluation of results and documentation<br />
<br />
* '''Submit Code and Final Evaluations(August 24-31): WER < 30%(with ~20,000 words in bidix) in both directions on most texts<br />
'''</div>Eden