RE: [xtm-wg] analysis of the meaning of ontology: pdf

["Paul Prueitt" <beadmaster@ontologyStream.com>]

The Waterson and Preece paper is at:

 http://www.csd.abdn.ac.uk/~apreece/Pubs/kbsj99b.html

Truly, I do not wish to take away from the expert systems approach to
knowledge representations.

I just point out that the task of exhaustively forming rules that capture
the cause and consequences of logical states that are conjectured to be
related to natural processes; well this is very hard to do.  When it is
done, there can be value.

Often it can appear to be done, and yet there may be a number of validation
mistakes that lead to poor correspondences in the real world.

The ontology itself does not depend on a rule based logic.  For example, the
ontology related to link analysis of transactions leads to a set of node
locations and relationships.  This can be converted directly into natural
language and provided to human as information about the ecosystem related to
these transactions.

The application of this type of technology to stock market prediction seems
to be on the horizon.

There is no need to represent the rules, just the concepts and some of the
relationships between concepts.  Let the human do the inference.  The
"rules" need never be enumerated.

In this way the ontology can stand by itself.

This is the alternative viewpoint.





------------------------ Yahoo! Groups Sponsor ---------------------~-~>
eGroups is now Yahoo! Groups
Click here for more details
http://click.egroups.com/1/11231/0/_/337252/_/980735302/
---------------------------------------------------------------------_->

To Post a message, send it to:   xtm-wg@eGroups.com

To Unsubscribe, send a blank message to: xtm-wg-unsubscribe@eGroups.com