I found two more articles regarding Information Extraction (IE) that look really useful
Sheffield University Natural Language Processing Group's Information Extraction User Guide (2nd Ed.)
and
Cowie J., Lehnert W., and Wilks Y.(1996), "Information Extraction", Communications of the ACM, Vol. 39, Iss. 1, pp.80-91
After I have gone through these I am also going to be looking at GATE as Graham Higgins suggested.
Previously I had discounted GATE because I felt it concentrated on Natural Language Processing (NLP) rather than Wrapper Induction (WI), but I need to look into this more. I had been looking into Jena, but it looks like Jena will only be able to deal with the Template Element (TE) production part of an IE system. I got this clarification from the Jena Development Group
More info on Jena can be found at
http://www.hpl.hp.com/semweb/tools.htm
and
href="http://jena.sourceforge.net/
More info on GATE can be found at
http://gate.ac.uk/
and
http://sourceforge.net/projects/gate
No comments:
Post a Comment