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

Reply via email to