Hi Benedikt,
It's been a while since I've done anything for Apertium, so my technical
knowledge has faded a bit, but if you ever would like to bounce
Dutch-language-stuff off me, just shoot me a mail. (My German is fairly bad
though.)
Pim
On Mon, Jun 9, 2014 at 5:18 PM, Benedikt Freisen <[email protected]> wrote:
> Good day!
>
> I recently stumbled upon Apertium, so when I found the apparently
> abandoned de-nl pair in incubator I took the liberty to tinker around
> with it for a few weeks.
> I already had a few things lying around for a while, for example a
> bilingual word list extracted from a wiktionary dump.
>
> Short summary of my work on de-nl:
> - both directions build
> - monodix's replaced by those from apertium-deu, apertium-nld
> - cleanup of the German monodix (do not use arbitrary inflected forms as
> lemma, sort, uniq, etc.)
> - massive extension of the bidix (for open word classes mostly scripted)
> - modifications to the monodix tag sets to simplify transfer
> - a few transfer rules for agreement of number, gender and case
>
> I would like to ask about the possibilities to share these improvements,
> and to possibly do regular work on this language pair.
>
> regards
> Benedikt Freisen
>
>
> PS: I originally wrote this mail yesterday, but since the membership
> confirmation mail got trapped in the spam folder I was not yet officially
> registered and it did not get through.
>
>
>
> ------------------------------------------------------------------------------
> HPCC Systems Open Source Big Data Platform from LexisNexis Risk Solutions
> Find What Matters Most in Your Big Data with HPCC Systems
> Open Source. Fast. Scalable. Simple. Ideal for Dirty Data.
> Leverages Graph Analysis for Fast Processing & Easy Data Exploration
> http://www.hpccsystems.com
> _______________________________________________
> Apertium-stuff mailing list
> [email protected]
> https://lists.sourceforge.net/lists/listinfo/apertium-stuff
>
------------------------------------------------------------------------------
HPCC Systems Open Source Big Data Platform from LexisNexis Risk Solutions
Find What Matters Most in Your Big Data with HPCC Systems
Open Source. Fast. Scalable. Simple. Ideal for Dirty Data.
Leverages Graph Analysis for Fast Processing & Easy Data Exploration
http://p.sf.net/sfu/hpccsystems
_______________________________________________
Apertium-stuff mailing list
[email protected]
https://lists.sourceforge.net/lists/listinfo/apertium-stuff
