Saturday, June 30, 2007, Pei Wang wrote:

PW> Since these projects start at concepts and inference, they won't be
PW> ready for NLP until the foundation is stable enough. The only one that
PW> has been doing NLP is SNePS, though its approach is not close to
PW> Hafstadter's.

That's my point. NLP isn't performed by reasoning engine, if at all. It's a
special case, and concepts-words have special status in the engine.

But diversity of challenges in reasoning itself seems to be greater
than what might be necessary for NLP. So why start at conceptual level?
Internal KR language can be used occasionally to steer pattern
formation and observe reasoning internals, and natural language can
be used for most of the teaching, from the very start.

-- 
 Vladimir Nesov                            mailto:[EMAIL PROTECTED]

-----
This list is sponsored by AGIRI: http://www.agiri.org/email
To unsubscribe or change your options, please go to:
http://v2.listbox.com/member/?member_id=231415&user_secret=e9e40a7e

Reply via email to