[Date Prev] | [Thread Prev] | [Thread Next] | [Date Next] -- [Date Index] | [Thread Index] | [Elist Home]
Subject: RE: [humanmarkup-comment] MOPS and such
http://www.ifs.org.uk/~popx/students/lectures/lect2/node4.html MOPS: Memory Organization Packets. Describes a concept (generalisation over several episodes), and contains two-level index. Level one is feature type; level two is feature value. Index points at sub-MOPs or individual episodes. len -----Original Message----- From: David Dodds [mailto:drdodds42@hotmail.com] Schank MOPs are a good first cut at fixed pattern situation detection but they suffer from the granularity / interstices problem that expert systems had. While BORIS, for example, did neat things it had the 'coverage' problem spoken about by Dreyfus. MOPs suffer from the frame problem. Kolodner, one of Schank's students, had some ideas on reducing the granularity problem. In my opinion it is a matcher problem. Instead of using only exact match one really needs to use 'similarity'. MOPs would be a good first cut though.
[Date Prev] | [Thread Prev] | [Thread Next] | [Date Next] -- [Date Index] | [Thread Index] | [Elist Home]
Powered by eList eXpress LLC