home *** CD-ROM | disk | FTP | other *** search
- Path: sparky!uunet!charon.amdahl.com!pacbell.com!decwrl!sun-barr!olivea!charnel!rat!usc!elroy.jpl.nasa.gov!swrinde!zaphod.mps.ohio-state.edu!uwm.edu!ogicse!das-news.harvard.edu!calliope!kehler
- From: kehler@calliope.uucp (Andy Kehler)
- Newsgroups: comp.ai
- Subject: Re: Loebner Turing test for Human like conversation
- Keywords: Loebner, turing, natural language
- Message-ID: <1992Nov6.021621.19294@das.harvard.edu>
- Date: 6 Nov 92 02:16:21 GMT
- References: <1992Nov5.212849.7986@cs.ucla.edu>
- Sender: usenet@das.harvard.edu (Network News)
- Organization: Aiken Computation Lab, Harvard University
- Lines: 39
-
- In article <1992Nov5.212849.7986@cs.ucla.edu> colby@oahu.cs.ucla.edu (Kenneth Colby) writes:
- >In the summer issue of AI Magazine, there is an article on the Loebner
- >Prize competition for most human-like computer conversationalist, wriiten by
- >Robert Epstein, director Cambridge Center for Behaviorial Studies.
- >
- >The competition involves Turing-like tests in using ordinary natural language
- >in a specific domain. Daniel C. Dennett is chairman of the prize committee.
- >The next competition will be held 12/15/92.
- >
- >Does anyone have any comments, criticisms, or suggestions about the article
- >or the competition.
- >
- >Ken Colby - Malibu Artifactual Intelligence Works
-
- I haven't read the article, but I heard about the competition second
- hand and read about it in the Boston Globe after it happened. IMHO,
- this competition serves no useful purpose whatsoever. The winner of
- the competition did so by picking the best "topic" ("whimsical
- sayings", I believe, hardly a real discussion topic -- compare with
- Shakespeare or wine, which I believe were others).
-
- From what I understand, all systems were at about the level of ELIZA
- (or worse). This led people to the conclusion that Natural Language
- Processing has made no progress in the last 25 years. This conclusion
- was made on the assumption that improving ELIZA-like programs is what
- NLP researchers have been trying to do during these years, an
- assumption that a competition like this helps to instill. To
- understate, this assumption is of course false.
-
- As a result, a competition like this gains nothing, and in fact hurts
- AI and NLP as valid fields of study (no flames on the 'valid field'
- issue please). I suggest that if Mr. Loebner wants to do something to
- further AI, he funnel his money into a research area of his liking, or
- underwrite a public television show that heightens awareness of what
- AI/NLP is really all about.
-
- My two cents.
-
- -- Andy Kehler
-