Newsgroups: comp.ai,comp.ai.fuzzy,comp.ai.nat-lang,comp.ai.shells
Path: cantaloupe.srv.cs.cmu.edu!das-news2.harvard.edu!fas-news.harvard.edu!newspump.wustl.edu!darwin.sura.net!gatech!howland.reston.ans.net!vixen.cso.uiuc.edu!uwm.edu!news.alpha.net!news.mathworks.com!uunet!psinntp!barilvm!aristo.tau.ac.il!libra.math.tau.ac.il!gary
From: gary@libra.math.tau.ac.il (Kshepitzki Gary)
Subject: Q: expert system needed
Message-ID: <1995Feb15.170930.10898@aristo.tau.ac.il>
Summary: Advice needed on choosing an Expert system.
Sender: usenet@aristo.tau.ac.il (USENET)
Organization: School of Math & CS - Tel Aviv University , Tel Aviv , ISRAEL.
X-Newsreader: TIN [version 1.2 PL2]
Date: Wed, 15 Feb 1995 17:09:30 GMT
Lines: 34
Xref: glinda.oz.cs.cmu.edu comp.ai:27528 comp.ai.fuzzy:4020 comp.ai.nat-lang:2911 comp.ai.shells:2160

Hello
I need some advice as for choosing an AI system.
We are running a very heavy application on a 486 PC with very
high CPU utilization. Our application is written in C and C++
and is interrupt driven (It has some characteristics of a
real time system).
We now want to add two AI features to the system. an expert system
and a natural language interpreter.
The natural language interpreter should understand a vocabulary
of 200 to 300 words.

Both the expert system and the interpreter are to be embedded
into our application, therefor they must be interfaced to C/C++
and preferably the rules of the expert system should be compilable
into code. We would also like to use fuzzy values in the ES.
Some last issues are that both app's must be light weight,
possibly reentrant, the resulting app' should be royalty free and
not one of the most expensive systems.

I have seen the following systems may comply with our needs as for
an expert system : RT_expert, CLIPS & Fuzzy CLIPS, ILOG RULES, M.4,
RAL and Rete++. Anybody knows anything about these systems ?
or has any opinion ? what about Nat' lang' interpreters ?

Any answer will be most welcom.
Please reply directly to me because I don't read news very often.

Thanks
	Gary K.

gary@math.tau.ac.il	(gary@libra.math.tau.il)



