RE: [agi] An Artificial General Intelligence in the Making

[Daniel Colonnese]

Title: Message

For those of us who are following the KNOW thread, could somebody comment on the capabilities of KNOW beyond existing knowledge representation language such as the ARFF format for the popular WEKA system.

 

I've input data into such a system before and while existing systems have extensive grammar for representing logical relations they have very limited capabilities for more ambiguous  knowledge.

 

The KNOW document Ben posted a link too says:

 

"Syntax to semantics mapping in the natural language module, in which the final result should be represented in this language;"

 

This kind of capabilities would certainly be a huge advance over something like ARFF.  If anyone works with ARFF, could he or she comment on the possibilities of such translation with the ARFF grammar?  Does anyone who's familiar with the technical workings of knowledge representation language have any idea on how this kind of mapping could be accomplished? 

 

-Daniel

*************************************
 Daniel Colonnese
 Computer Science Dept. NCSU
 2718 Clark Street
 Raleigh NC 27670
 Voice: (919) 451-3141
 Fax: (775) 361-4495
 http://www4.ncsu.edu:8030/~dcolonn/
*************************************

-----Original Message-----
From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED]] On Behalf Of Gus Constan
Sent: Sunday, February 02, 2003 8:12 PM
To: [EMAIL PROTECTED]
Subject: RE: [agi] An Artificial General Intelligence in the Making

Hi Ben;

Would you kindly provide a valid url for Knowledge Representation for Inference

in your reference document www.goertzel.org/papers/KNOWSpecification.htm

 

thanks

 

Gus