Newsgroups: comp.ai
Path: cantaloupe.srv.cs.cmu.edu!das-news2.harvard.edu!news2.near.net!news.mathworks.com!news.duke.edu!news-feed-1.peachnet.edu!gatech!newsxfer.itd.umich.edu!zip.eecs.umich.edu!umn.edu!krill!tauz0001
From: tauz0001@krill.micro.umn.edu (DAVID C TAUZELL)
Subject: A better FAQ
Message-ID: <CyJxJB.6Kt@news.cis.umn.edu>
Keywords: fawqq
Sender: news@news.cis.umn.edu (Usenet News Administration)
Nntp-Posting-Host: krill.itlabs.umn.edu
Organization: University of Minnesota, Minneapolis: Under Grad Workstation Lab.
Date: Mon, 31 Oct 1994 19:19:14 GMT
Lines: 23

It is always the problem that people write in with questions that have
either just been discussed, or are basic question that are covered in the FAQ.

It seems reasonable that one would look in the FAQ first, and I totally agree
with that.  It saves lots of valuable space on the net. But I have a better
idea.  I"m not 100% sure how well this would work, but here goes.

A program would constatly read the newsgroups and attemp to extract the
questions and answers and then put them into some sort of database that
anyone could accses.. Perhaps via mosaic (I know that not everyone has
accses to the WWW, but htis is just an idea)... It would also have all the
questions to the FAQ in it.  To ask a question you would just type it in
the way you would in english and the computer would try and make some sense
out of what you just said.  If this didn't work, there would be some way
of limiting your question bye the use of keyword, like the way and 
computerized card catalog works.

Does anybody have any ideas on the feasability of this?  Or at the very least
of a good interface to the FAQ's. 

Well, that'`s my nine cents.
bye.

