Corpora: training Brill's tagger with French

[Torbjörn Lager]

Andre Linden wrote:

>       We are currently working with Brill's tagger on French texts. We
> are facing the problem of training the tagger with accented texts and
> would like to know if anyone already has encountered this problem. We
> would very much appreciate any feedback on your own experience in this
> regard.

You may want to know about an alternative transformation-based learner:
The µ-TBL system:

    http://stp.ling.uu.se/~torbjorn/mutbl.html

Maybe overkill, maybe not. Depends on what you want to do...

Best regards,
Torbjörn

--
----------------------------------------------------------------
Torbjörn Lager                  Computational Linguist
Department of Linguistics       Uppsala University
S-751 20 Uppsala                Sweden
Phone: +46 18 471 7860          http://stp.ling.uu.se/~torbjorn/
----------------------------------------------------------------