Hi Денис and all,

Do we even know yet whether Apertium will be in gsoc 2017?

I'm working at the moment on automatic generation of constraint
grammar (CG) rules from text corpus. I haven't had time to test yet
how good rules it generates
(http://svn.code.sf.net/p/apertium/svn/branches/mil-pos-tagger/ is
using parallel corpus approach but it is easily converted to non
parallel version). If MIL learning of prolog constraint grammar like
rules from non parallel corpus gives good result then there would be
some work to convert the thing to actually make real constraint
grammar rules.

And so how I think this relates to data science is that it extracts
the grammar (=knowledge) from the text corpus. Not sure if data
science deals with that but that is the image I got from wikipedia.

-Joonas

On 10/2/16, Денис Сенькин <[email protected]> wrote:
> Are there any Apertium projects, that require Data Science and Analysis?
> And will there be availible for GSOC 2017?
>

------------------------------------------------------------------------------
Check out the vibrant tech community on one of the world's most 
engaging tech sites, SlashDot.org! http://sdm.link/slashdot
_______________________________________________
Apertium-stuff mailing list
[email protected]
https://lists.sourceforge.net/lists/listinfo/apertium-stuff

Reply via email to