Fran et al:
> The main thing is that it would make it easier to train taggers for use
> after CG. For many language pairs, defining the .tsx file is quite
> cumbersome if the tagset is large. And with an automatically-defined
> tagset, the training does not finish because it is too large.
Yes, it would help a lot. I was wondering if one could derive a tagset 
automatically by using a partition of what is defined in the CG file (by 
partition I mean that in the case that two overlapping classes A and B, 
it would generate three non-overlapping classes: A–B, A⋂B, and B–A. I 
wonder if this can be done automatically.
>> >It would be nice to have this feature, but I think this is a bit out of
>> >the scope of Gang's project.
> Ok, no problem:)
Well, if Gang wants to go the extra mile I'm sure we would all welcome 
the addition, but, as I said, this would be orthogonal to his work: this 
is something that would be desirable both for hidden Markov model 
taggers and (light) sliding window taggers.

Cheers

Mikel

-- 
Mikel L. Forcada (http://www.dlsi.ua.es/~mlf/)
Departament de Llenguatges i Sistemes Informàtics
Universitat d'Alacant
E-03071 Alacant, Spain
Phone: +34 96 590 9776
Fax: +34 96 590 9326


------------------------------------------------------------------------------
LIMITED TIME SALE - Full Year of Microsoft Training For Just $49.99!
1,500+ hours of tutorials including VisualStudio 2012, Windows 8, SharePoint
2013, SQL 2012, MVC 4, more. BEST VALUE: New Multi-Library Power Pack includes
Mobile, Cloud, Java, and UX Design. Lowest price ever! Ends 9/22/13. 
http://pubads.g.doubleclick.net/gampad/clk?id=64545871&iu=/4140/ostg.clktrk
_______________________________________________
Apertium-stuff mailing list
[email protected]
https://lists.sourceforge.net/lists/listinfo/apertium-stuff

Reply via email to