Newsgroups: comp.ai.nat-lang
Path: cantaloupe.srv.cs.cmu.edu!das-news.harvard.edu!news2.near.net!MathWorks.Com!yeshua.marcam.com!charnel.ecst.csuchico.edu!csusac!csus.edu!netcom.com!netcom3!jrd
From: jrd@netcom3.netcom.com (Jon Degenhardt)
Subject: Re: Books on Intro. natural language proces
In-Reply-To: chrisb@cs.cornell.edu's message of Tue, 27 Sep 1994 02:06:33 GMT
Message-ID: <JRD.94Sep28001212@netcom3.netcom.com>
Sender: jrd@netcom.com (Jon Degenhardt)
Organization: NETCOM On-line services
References: <TED.94Sep23121916@kyklopon.crl.nmsu.edu> <3608t2$eo9@news.cais.com>
	<1994Sep25.174751.28787@cs.cornell.edu>
	<1994Sep25.230427.29778@iitmax.iit.edu>
	<1994Sep27.020633.16498@cs.cornell.edu>
Date: Wed, 28 Sep 1994 07:12:11 GMT
Lines: 36

In article <1994Sep27.020633.16498@cs.cornell.edu> chrisb@cs.cornell.edu (Chris Buckley) writes:

>sanders@iitmax.iit.edu (Greg Sanders) writes:

>>Let's recast the problem.  Suppose we don't just
>>want to retrieve the document.  Suppose the system must be able to 
>>answer questions about it and to generate a paragraph saying *why* 
>>you will think the document is of interest.  I believe this shows how 
>>the arguments you are advancing are misstated.  You seem to mean only 
>>that the approaches you are defending result in the right selection of 
>>documents.  

>>It is just plain wrong to say these approaches constitute any sort of 
>>understanding of the documents.  Recasting the task as I have done
>>above makes clear how these approaches cannot perform any task that
>>requires real understanding of the text.  

>It's not at all clear! Even using your somewhat slanted tasks:
>   1. The system can certainly correctly answer a lot of questions about
>the document.  Eg. about your response here : "Did the message
>discuss NLU?".  "Was your message about apples?"
>   2. A possible paragraph: "Your article was about NLU and IR because
>'NLU' was the most highly weighted term in the article and 'IR' was
>the fifth highest weighted term".

Perhaps someone could provide a more precise definition of tasks which are
considered by definition NLU and which are NLP. From a pragmatic point of
view, many tasks require a level of "understanding" of text which falls in
a gray area between my rather imprecise understanding of the definitions of
these two terms. Are business card readers (five or six commercially
available) performing an NLP task or an NLU task? Which category is Machine
Translation in? Document summarization? From a pragmatic point of view,
these definitions depend on task, rather than the underlying problem
solving mechanism, right? 

--Jon
