On 7 October 2011 23:44, Hector <[email protected]> wrote: > Hi! > I'm trying to contribute to the en-es pair by adding some currently > unknown words to the dictionaries, and realized that assigning > paradigms can be very time consuming. Asked on irc about it, and > spectre suggested these papers: > > "Enlarging monolingual dictionaries for machine translation with > active learning and non-expert users" > "Multimodal building of monolingual dictionaries for machine > translation by non-expert users" > > found them here (without links, though): > http://www.dlsi.ua.es/~japerez/pub/index.html >
I looks like the first is yet to be published, and the second was a few weeks ago, so it may be a while yet before they're in general circulation. I imagine the implementation is this: http://apertium.svn.sourceforge.net/viewvc/apertium/branches/apertium-dixtools-paradigmlearning/ - which infers the paradigm from a corpus. It might just be easier all round if you add to the bidix and send me the revision number, and I'll add the monolingual entries. -- <Sefam> Are any of the mentors around? <jimregan> yes, they're the ones trolling you ------------------------------------------------------------------------------ All of the data generated in your IT infrastructure is seriously valuable. Why? It contains a definitive record of application performance, security threats, fraudulent activity, and more. Splunk takes this data and makes sense of it. IT sense. And common sense. http://p.sf.net/sfu/splunk-d2dcopy2 _______________________________________________ Apertium-stuff mailing list [email protected] https://lists.sourceforge.net/lists/listinfo/apertium-stuff
