https://wiki.apertium.org/w/index.php?action=history&feed=atom&title=User%3AEden%2FGSOC2020Proposal_English-Swahili 2026-04-09T10:59:35Z Revision history for this page on the wiki MediaWiki 1.34.1 https://wiki.apertium.org/w/index.php?title=User:Eden/GSOC2020Proposal_English-Swahili&diff=71909&oldid=prev 2020-03-31T13:21:18Z

<p></p> <a href="//wiki.apertium.org/w/index.php?title=User:Eden/GSOC2020Proposal_English-Swahili&amp;diff=71909&amp;oldid=71655">Show changes</a>

Eden https://wiki.apertium.org/w/index.php?title=User:Eden/GSOC2020Proposal_English-Swahili&diff=71655&oldid=prev 2020-03-28T10:59:11Z

<p>Created page with &quot;== My goal == I’m planning to work on the ‘English-Swahili’ language pair.&lt;br/&gt; From last year&#039;s work on the eng-lin pair, there are 2 main areas I will improve on for t...&quot;</p> <p><b>New page</b></p><div>== My goal ==<br /> I’m planning to work on the ‘English-Swahili’ language pair.&lt;br/&gt;<br /> From last year&#039;s work on the eng-lin pair, there are 2 main areas I will improve on for this year: daily communication with my mentors and having enough Swahili language data. <br /> <br /> == (TODO) Why am I interested in Apertium? ==<br /> Apertium is at the intersection of computers and languages, which are two of my passions.<br /> <br /> <br /> == Who will benefit and why should it get sponsored ==<br /> <br /> African languages are poorly represented in Apertium and even other commercially available options are usually quite lacking. Given that Swahili, and most African languages do not always have a lot of digitized content accessible, it&#039;s hard to use any machine learning or NLP tools to build translators since massive amount of data for these languages do not exist. In such cases, a rule-based MT tool like Apertium becomes the most viable option.<br /> <br /> == (TODO) Swahili resources ==<br /> Here is a list of &#039;&#039;open&#039;&#039; and &#039;&#039;public domain&#039;&#039; resources(dictionaries, grammar books, texts, etc) for Swahili:&lt;br/&gt;<br /> <br /> == (TODO) Coding challenge ==<br /> All my work are in 2 main repos: [https://github.com/thefreezer/apertium-swa apertium-swa] [https://github.com/thefreezer/apertium-swa-eng apertium-swa-eng] &lt;br /&gt;<br /> <br /> == (TODO) Work plan ==<br /> community bonding period <br /> - Swahili corpus from Wikipedia(Done)<br /> - Frequency List<br /> - Work on transfer rules and CG<br /> <br /> Week 1: <br /> - adding nouns(from frequency list) in the lin transducer<br /> <br /> Week 2:<br /> - adding pronouns and adjectives in the swa transducer <br /> <br /> Week 3: <br /> - polishing the transducer to give better analyses<br /> <br /> Week 4: <br /> - transfer rules for nouns and adjectives(both directions)<br /> <br /> * &#039;&#039;&#039;Deliverable #1&#039;&#039;&#039; ...<br /> <br /> Week 5: <br /> - continue work on bilingual dictionary,<br /> <br /> Week 6: <br /> - filling pronouns, adverbs, and others in the bidix<br /> <br /> Week 7: <br /> - adding determinants and more adjectives in the bidix<br /> <br /> Week 8: <br /> - continue work on transfer rules in .t2x and t3x files<br /> <br /> * &#039;&#039;&#039;Deliverable #2&#039;&#039;&#039; ...<br /> <br /> Week 9 :<br /> - continue work on disambiguation(both directions)<br /> <br /> Week 10:<br /> - work on transfer rules, <br /> <br /> Week 11:<br /> - continue work on transfer rules and testing, <br /> <br /> Week 12:<br /> - filling bidix with miscellaneous words <br /> <br /> * &#039;&#039;&#039;Project completed&#039;&#039;&#039; ...<br /> <br /> == Skills and qualifications ==<br /> Ongoing major: second year Computer Science students with a minor in Math&lt;br /&gt;<br /> Relevant technical skills: python, c/c++, sql(intermediate), git(intermediate), bash(intermediate), html5/css3(advanced)&lt;br /&gt;<br /> Languages: French(native), Lingala(native), English(Fluent) , Swahili(proficient), Tshiluba(proficient), Twi(elementary)&lt;br /&gt;<br /> <br /> == Non-Summer-of-Code plans ==<br /> None.</div>

Eden