Thinking Clearly - Latest Comments in NLTK: NLP in Python

Re: NLTK: NLP in Python

Alex Shkotin — Sat, 07 Jun 2008 05:03:18 -0000

And may be you have a look at http://attempto.ifi.uzh.ch/... as they have CNL 2 OWL parser.

Re: NLTK: NLP in Python

Bijan Parsia — Fri, 24 Nov 2006 02:00:53 -0000

Oh! thanks Steven!

Re: NLTK: NLP in Python

Steven Bird — Thu, 16 Nov 2006 05:40:02 -0000

You wrote: "Alas, the NLTK-Lite tutorial is just a set of slides" -- in fact it is currently 250 pages of freely downloadable textbook. Please see http://nltk.sf.net/lite/doc...

Re: NLTK: NLP in Python

Bijan Parsia — Tue, 10 Oct 2006 04:42:53 -0000

Thanks for the links! I'll check them out.

I'm aware of the difference and what seems to be the current preferred approach (stats).

The commonsense based one looks absolutely fascinating! And very useful for my current class. Thanks again.

Re: NLTK: NLP in Python

Dibau — Mon, 09 Oct 2006 04:36:37 -0000

You should also check out ConceptNet & it's underlying Multilingua:
http://web.media.mit.edu/~h...
http://web.media.mit.edu/~h...

Both are also Python-based & very impressive (based on user-generated common-sense knowledge-base).

Regarding books: you'll see that there are 2 paradigms (logic vs. statistics). The logic-approach (such as in Allen's book) works nicely but requires a lot of tedious maintenance. Personally I believe more in the statistics approach (such as in Manning & Schuetze's book), which seems like the more strategically sound paradigm.