All the Perl that's Practical to Extract and Report

extracting stuff from text

TeeJay on 2003-09-27T09:50:25

Lathos pointed me at GATE - General Architecture for Text Engineering, which looks pretty cool.

He also pointed at his very cool Lingua::EN::NamedEntity module which looks very interesting.

I also found some interesting essays on the global interweb highway :
Mining dates from historical documents by Dana Mckay (University of Waikato)
and
SEMIAUTOMATIC GENERATION OF RESILIENT DATA-EXTRACTION ONTOLOGIES by Yihong Ding

Bad link

vsergu on 2003-09-27T11:44:07

That "date" paper sounds interesting, but it's password protected. I did manage to find a copy. I hope that link is persistent. If not, try the cache link on this page.

Re:Bad link

TeeJay on 2003-09-27T18:17:58

wierd - it worked for me and I didn't put in a password.