LINGUIST List 9.310

Tue Mar 3 1998

Disc: NLP and Syntax

Editor for this issue: Brett Churchill <brettlinguistlist.org>

Directory

1. Philip A. Bralich, Ph.D., NLP and EAGLES
2. Sam Salt, Re: 9.305, Disc: NLP and Syntax
3. Samuel L. Bayer, NLP and Syntax

At 03:10 AM 2/23/98 -1000, jockccl.umist.ac.uk wrote:
>Although mindful of the risk of exposing us all to Saint Anthony's
>Fire, I wish to respond to the criticism of the EAGLES initiative 
>made by Dr Bralich. I do so in my function as co-Chief Editor of 
>EAGLES.
>
>There is a simple reason why EAGLES does not mention the criteria
>espoused by Dr Bralich: EAGLES has not so far concerned itself
>with proposing standards in the area of parsers.
>
>That is the short answer, interested readers please read on.
>
>It is unfair to criticise us for not doing something we had not 
>included in our (public) programme of work. One may criticise the 
>initial selection of topics, however. The topics retained were 
>those where there was wide agreement that some kind of useful 
>consensus could be obtained in the near term. The set of topics 
>we actually worked on were furthermore constrained by factors 
>such as availability of voluntary labour.

Point taken. I agree and apologize. I will refrain from further
commentary on this matter, and if EAGLES does want to propose
standards for the area of parsers, I would be happy to volunteer
time and effort. (CV available upon request).

Phil Bralich


Philip A. Bralich, Ph.D.
President and CEO
Ergo Linguistic Technologies
2800 Woodlawn Drive, Suite 175
Honolulu, HI 96822

Tel: (808)539-3920
Fax: (808)539-3924

Message 2: Re: 9.305, Disc: NLP and Syntax

It seems to me that Philip Brahlich and his BracketDoctor are coming in for
some fairly heavy criticism although I am not at all sure that it is
deserved. Maybe it depends on whether you are a scientist or a
technologist. My major professional interest is in getting NLP systems that
can be implemented on computer and that can do useful work. Whilst I am
fascinated by all the necessary theorising that goes on in linguistics, it
isn't much good unless it can be tested realistically.

I'm not saying BracketDoctor is perfect, nor have I had time to fully
evaluate it but I can say it works better than any other NLP software I've
tried to date. I can see that his style is quite aggressive and that there
is a significant element of advertising but that shouldn't detract from the
success of the system. For my part it is a real pleasure to see something
that works rather than yet more theory. 

Sam Salt
*********************************
Sam Salt
Head of Division of Computing
University of Derby
Kedleston Road
Derby
DE22 1GB

01332-622222
Ext:1753

e-mail: d.w.saltderby.ac.uk
********************************

Relative to the Derek Bickerton/Philip Bralich parser adequacy
criteria: the field of computational linguistics has spent quite a
number of years developing evaluation criteria for parsers, which I
recommend looking at before you start reinventing the wheel. See the
journal Computational Linguistics for the last five or six years or so,
or for a summary, you can read the chapter that my coworkers and I wrote
on comparing the theoretical and corpus-based computational enterprises,
in a book edited by John Lawler called Computers and Linguistics, due
out in April.

Cheers,
Sam Bayer
sammitre.org