Search results

|title=expand coverage of Kyrgyz to English structural transfer |mentors=JNW, sevilay, Unhammer, marcriera, padth4i, Oguz, popcorndude

...imzyan]] [[User:Xavivars]] [[User:Bech]] [[User:Jimregan|Jimregan]] [[User:Unhammer]] [[User:Fsanchez]] [[User:Nikant]] [[User:Fulup|Fulup]] [[User:Japerez]] [ ...rule|Read more]]... || [[User:Mlforcada]] [[User:ilnar.salimzyan]] [[User:Unhammer]] [[User:Nikant]] [[User:Fulup|Fulup]] [[User:Juanpabl]]

* Unhammer's [[User:Unhammer/wishlist|wishlist]] ...lation pair to releasable quality. This would entail obtaining good naïve coverage and a clean [[testvoc]].

...alyser || While the current bn-en morphological analyser has a pretty good coverage, it should have been higher. Part of the reason is that a lot of verbs have ...pair HOWTO]] into Nynorsk. ||align=center| 5–8 || [[User:Unhammer|Unhammer]]

...tatus checks can be anything from code linting, unit/integration tests and coverage tools (i.e. continuous integration). These tools have to be configured at a ...realise most people don't care. --[[User:Unhammer|unhammer]] ([[User talk:Unhammer|talk]]) 12:44, 9 February 2018 (CET)

...olkit portion of the project consists of tools such as regression testing, coverage testing, vocabulary testing and statistics storage, while the framework is Author: Kevin Brubeck Unhammer <unhammer@fsfe.org>

Once a transducer has ~80% coverage on a range of medium-large corpora we can say it is "working". Over 90% and !rowspan=2| coverage

I'll need help to set up coverage-measuring scripts and to learn how I can testvoc only certain POS's. Tomorrow I am going to translate this additional Tatar ones (to boost up the coverage - they seem to be quite frequent!) and work on transfer rules if they are n

...esults; within about 2 weeks (and during my exams period) we got to a ~80% coverage of the Maltese corpora. This way we easily got good enough coverage of nouns, verbs, adjectives, etc.

...an=2| 0.6.1 || nno → nob ||rowspan=2 {{yes}} || - || - || - ||rowspan=2| Unhammer and Trosterud, 2009<br/> (two reference translations; as of [https://github == Coverage and Dictionary size ==

==Norwegian Nynorsk and Bokmål (Unhammer)== ...ing the most frequency used missing words. Right now we have a roughly 68% coverage of the 20K most freq used words. At first I was strictly focused on creatin

Once a transducer has ~80% coverage on a range of medium-large corpora we can say it is "working". Over 90% and !rowspan=2| coverage

...translator is very high, and compares with commercial systems -- over 95% coverage (around 5 unknown words out of 100 words), and between 3-7% word-error rate ...ken up again in 2009 during the Google Summer of Code competition by Kevin Unhammer, a masters' student in computational linguistics at the University of Berge

...translator is very high, and compares with commercial systems -- over 95% coverage (around 5 unknown words out of 100 words), and between 3-7% word-error rate ...ken up again in 2009 during the Google Summer of Code competition by Kevin Unhammer, a masters' student in computational linguistics at the University of Berge

...translator is very high, and compares with commercial systems -- over 95% coverage (around 5 unknown words out of 100 words), and between 3-7% word-error rate ...ken up again in 2009 during the Google Summer of Code competition by Kevin Unhammer, a masters' student in computational linguistics at the University of Berge

...'': <section begin=rlx_rules />32<section end=rlx_rules /> as of r57680 by unhammer ~ [[User:StemCounterBot|StemCounterBot]] ([[User talk:StemCounterBot|talk]] * coverage: ~<section begin=wikipedia-coverage />85.3<section end=wikipedia-coverage />%

...it was a long way from finished. '''[http://unhammer.wordpress.com/ Kevin Unhammer]''' from the ...ot all of the goals were realised, but we were able to make the first wide-coverage [http://en.wikipedia.org/wiki/Morphology_(linguistics) morphological analys