<div dir="ltr">I'd also suggest JCarafe, a CRF written in Java (Scala, actually) and includes maxent classifiers and brown clustering implementations.</div><div class="gmail_extra"><br clear="all"><div>______________<br>
<a href="mailto:craig.pfeifer@gmail.com">craig.pfeifer@gmail.com</a></div>
<br><br><div class="gmail_quote">On Mon, Dec 2, 2013 at 5:57 PM, Grzegorz Chrupała <span dir="ltr"><<a href="mailto:pitekus@gmail.com" target="_blank">pitekus@gmail.com</a>></span> wrote:<br><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">
Hi Saeed,<br>
<br>
You'll need an implementation of a sequence labeling algorithm. You<br>
may want to try one of these:<br>
- Wapiti. Implements conditional random fields and maximum entropy<br>
Markov models: <a href="http://wapiti.limsi.fr/" target="_blank">http://wapiti.limsi.fr/</a><br>
- Sequor. Implements sequence perceptron. <a href="https://bitbucket.org/gchrupala/sequor" target="_blank">https://bitbucket.org/gchrupala/sequor</a><br>
<br>
Both of these allow you to define your own features and train on your own data.<br>
<br>
Best luck,<br>
--<br>
Grzegorz Chrupała<br>
Communication and Information Sciences<br>
Tilburg University<br>
PO Box 90153<br>
5000 LE Tilburg<br>
The Netherlands<br>
<br>
Web: <a href="http://grzegorz.chrupala.me" target="_blank">grzegorz.chrupala.me</a><br>
Phone: +31 13 466 3106<br>
Email: <a href="mailto:g.chrupala@uvt.nl">g.chrupala@uvt.nl</a><br>
<div class="HOEnZb"><div class="h5"><br>
<br>
<br>
On Mon, Dec 2, 2013 at 8:33 PM, Saeed Farzi <<a href="mailto:saeedfarzi@gmail.com">saeedfarzi@gmail.com</a>> wrote:<br>
> I need a chunker that i can train it with my special tags and features.<br>
><br>
><br>
> --<br>
> S.Farzi, Ph.D. Student<br>
> Natural Language Processing Lab,<br>
> School of Electrical and Computer Eng.,<br>
> Tehran University<br>
> Tel: +9821-6111-9719<br>
><br>
> _______________________________________________<br>
> UNSUBSCRIBE from this page: <a href="http://mailman.uib.no/options/corpora" target="_blank">http://mailman.uib.no/options/corpora</a><br>
> Corpora mailing list<br>
> <a href="mailto:Corpora@uib.no">Corpora@uib.no</a><br>
> <a href="http://mailman.uib.no/listinfo/corpora" target="_blank">http://mailman.uib.no/listinfo/corpora</a><br>
<br>
_______________________________________________<br>
UNSUBSCRIBE from this page: <a href="http://mailman.uib.no/options/corpora" target="_blank">http://mailman.uib.no/options/corpora</a><br>
Corpora mailing list<br>
<a href="mailto:Corpora@uib.no">Corpora@uib.no</a><br>
<a href="http://mailman.uib.no/listinfo/corpora" target="_blank">http://mailman.uib.no/listinfo/corpora</a><br>
</div></div></blockquote></div><br></div>