Newsgroups: comp.ai.nat-lang
Path: cantaloupe.srv.cs.cmu.edu!das-news2.harvard.edu!news2.near.net!news.mathworks.com!uhog.mit.edu!bloom-beacon.mit.edu!usc!cs.utexas.edu!news.sprintlink.net!demon!uknet!newsfeed.ed.ac.uk!edcogsci!usenet
From: chrisbr@cogsci.ed.ac.uk (Chris Brew)
Subject: Re: Q: Teaching material for statistical CL
In-Reply-To: Joakim Nivre's message of Fri, 16 Jun 1995 13:29:10 GMT
Message-ID: <CHRISBR.95Jun19142139@blair.cogsci.ed.ac.uk>
Sender: usenet@cogsci.ed.ac.uk (C News Software)
Nntp-Posting-Host: blair
Organization: Centre for Cognitive Science, University of Edinburgh
References: <DA9pGn.K5B@news.gu.se>
Date: Mon, 19 Jun 1995 13:21:39 GMT
Lines: 78

In article <DA9pGn.K5B@news.gu.se> Joakim Nivre <joakim> writes:

   Path: edcogsci!newsfeed.ed.ac.uk!str-ccsun!zippy.dct.ac.uk!yama.mcc.ac.uk!sunsite.doc.ic.ac.uk!agate!dog.ee.lbl.gov!overload.lbl.gov!lll-winken.llnl.gov!uwm.edu!cs.utexas.edu!convex!cnn.exu.ericsson.se!erinews.ericsson.se!sunic!sunic.sunet.se!news.chalmers.se!news.gu.se!news
   Newsgroups: comp.ai.nat-lang
   From: Joakim Nivre <joakim>
   Date: Fri, 16 Jun 1995 13:29:10 GMT
   Sender: news@news.gu.se (USENET News System)
   Organization: Gothenburg University
   Content-Type: text/plain; charset=iso-8859-1
   Nntp-Posting-Host: esperanto.ling.gu.se
   Content-Transfer-Encoding: quoted-printable
   Mime-Version: 1.0
   X-Mailer: Mozilla 1.1b3 (X11; I; SunOS 4.1.3_U1 sun4m)
   X-Url: news:comp.ai.nat-lang
   Lines: 22

   Dear all,

   I am going to develop a course on statistical methods and models
   in computational linguistics using Eugene Charniak's book "Statistical
   Language Learning". I would be very grateful for advice concerning:

   1. Supplementary literature, especially for the mathematical background,
      probability theory, etc., but also for applications.

   2. Material for practical exercises, mini-projects, etc., both written
      documentation and software if available.

   I'd be happy to post a summary if there is interest.

   Best regards,

   Joakim Nivre

   Department of Linguistics
   G=F6teborg University
   E-mail: joakim@ling.gu.se
I have been doing the same sort of thing in a small way, and have put
some preliminary materials on http://www.cogsci.ed.ac.uk/~chrisbr/charniak.html
These will be undergoing further development in the coming weeks, and I'd
welcome constructive feedback:

What there is is: 

1) a small corpus and Prolog program for generating it. The idea
is that people try out the techniques in Charniak, and the
design principle for my program was that it should produce
something as English-like as possible using a tiny
vocuabulary and a very simple domain.

2) Some simple programs written in Unix shell and AWK, designed
to show how to calculate entropy and the like.

3) A few paragaphs of introduction to Chapters 1 and 2 of Charniak.

I'd be interested in anything else people have in this area. I am
replying immediately, even though I feel that what I have is
unfinished. I hope others will do the same, since I think the
need for tutorial material in this area is urgent.

Chris
--
------------------------------------------------------------------
Dr Chris Brew, 
Language Technology Group, 
The University of Edinburgh
Human Communication Research Centre
------------------------------------------------------------------
Email: Chris.Brew@edinburgh.ac.uk
Work Address:   HCRC, 2 Buccleuch Place,  Edinburgh EH8 9LW 
                Scotland
Work Telephone: +44 131 650 4631 
Work fax:       +44 131 650 4587
------------------------------------------------------------------
Home Address:   13 Kilmaurs Road,          Edinburgh EH16 5DA 
                Scotland    Home    Telephone: (+44   131    662  0574)
------------------------------------------------------------------ 

