ANNOUNCE: brillig 0.3 - not quite the Brill tagger

Grzegorz Chrupała pitekus at
Wed Sep 7 12:32:17 BST 2011

Hey Eric and all,

> One other thing, is looking through hackage, I notice Grzegorz
> Chrupała's sequor package which from the description sounds like
> something brillig could try to use (it's meant to provide a family
> of POS taggers)...

I think I don't get it. How would you use a discriminatively trained
tagger like sequor in combination with the Brill tagger?

For what it's worth, I just trained Sequor  (using several spelling
features as encoded in the data/mlcomp2.features template) on the
initial 90% of the Brown corpus, and tested on the final 10%, and got
an accuracy of 96.2%. Training takes several hours, but tagging runs
at more than 3000 words/second.

Grzegorz Chrupała
Saarland University
FR 7.4 Spoken Language Systems
Building C7 1, Room 0.04
66041 Saarbrücken
+49 681 302 58126

More information about the NLP mailing list