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.
Bijan Parsia
· 3 years ago
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.
Steven Bird
· 3 years ago
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/en/
All Comments
http://web.media.mit.edu/~hugo/conceptnet/
http://web.media.mit.edu/~hugo/montylingua/
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.
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.