On 12/3/2010 5:48 PM, John Bottoms wrote:
> IBM has made significant progress with a hybrid system that incorporates
> semantic and statistical analysis to find answers to Jeopardy questions.
> ...
> Could this be done within OWL by masquerading or encapsulating?
> Or would a new structure be required? (01)
The short answer is no. (02)
OWL was deliberately limited in capability, and it was designed for
processing RDF data. (03)
AI projects such as IBM's system, Cyc, our VivoMind work, and many
other systems for NLP use much richer and more complex knowledge
representation and reasoning systems than OWL. And they use far
more efficient data representations than RDF. (04)
OWL was never designed for AI or NLP. (05)
John Sowa (06)
_________________________________________________________________
Message Archives: http://ontolog.cim3.net/forum/ontolog-forum/
Config Subscr: http://ontolog.cim3.net/mailman/listinfo/ontolog-forum/
Unsubscribe: mailto:ontolog-forum-leave@xxxxxxxxxxxxxxxx
Shared Files: http://ontolog.cim3.net/file/
Community Wiki: http://ontolog.cim3.net/wiki/
To join: http://ontolog.cim3.net/cgi-bin/wiki.pl?WikiHomePage#nid1J
To Post: mailto:ontolog-forum@xxxxxxxxxxxxxxxx (07)
|