From: Mari Broman Olsen (molsen@astrid.ling.nwu.edu)
Date: Tue Jul 16 1996 - 12:09:08 EDT
Forwarded message:
>From no-reply@xxx.lanl.gov Mon Jul 15 05:32:19 1996
Date: Mon, 15 Jul 1996 04:39:50 -0600
Message-Id: <199607151039.AA252407190@xxx.lanl.gov>
Precedence: bulk
Note: e-print archive software written by PG at LANL (8/91,12/92,11/93) GTDA
Now-Supported-By: the National Science Foundation under Agreement No. 9413208
From: no-reply@xxx.lanl.gov (send mail ONLY to cmp-lg)
Reply-To: cmp-lg@xxx.lanl.gov
To: rabble@xxx.lanl.gov (cmp-lg daily title/abstract distribution)
Subject: cmp-lg daily 9607014 -- 9607017 received (over 1288 served) 1226
******************************************************************************
The Computation and Language E-Print Archive
CMP-LG@XXX.LANL.GOV
http://xxx.lanl.gov/cmp-lg/
LISTINGS and NEWS
for today updated May 14, 1996
******************************************************************************
TITLE/AUTHOR/ABSTRACT LISTINGS
received from Fri Jul 12 00:07:36 MDT 1996 to Mon Jul 15 00:07:34 MDT 1996
------------------------------------------------------------------------------
\\
Paper: cmp-lg/9607014
From: Barbara.Dieugenio@itri.brighton.ac.uk (Barbara DiEugenio)
Date: Fri, 12 Jul 1996 12:09:21 +0100 (BST)
Title: A Corpus Study of Negative Imperatives in Natural Language Instructions
Author: Keith Vander Linden (University of Brighton), Barbara Di Eugenio
(Carnegie Mellon University)
Comments: 6 pages, uses colap.sty and acl.bst
Journal-ref: Proceedings of COLING 96 (Copenhagen)
\\
In this paper, we define the notion of a preventative expression and discuss
a corpus study of such expressions in instructional text. We discuss our coding
schema, which takes into account both form and function features, and present
measures of inter-coder reliability for those features. We then discuss the
correlations that exist between the function and the form features.
\\ (cmp-lg/9607014 , 11kb)
------------------------------------------------------------------------------
\\
Paper: cmp-lg/9607015
From: Barbara.Dieugenio@itri.brighton.ac.uk (Barbara DiEugenio)
Date: Fri, 12 Jul 1996 19:27:10 +0100 (BST)
Title: Learning Micro-Planning Rules for Preventative Expressions
Author: Keith Vander Linden (ITRI, University of Brighton); Barbara Di Eugenio
(Computational Linguistics, Carnegie Mellon University)
Comments: 8 pages, 4 Postscript figures, uses colap.sty
Journal-ref: INLG96 -- Eight International Natural Language Generation Workshop
\\
Building text planning resources by hand is time-consuming and difficult.
Certainly, a number of planning architectures and their accompanying plan
libraries have been implemented, but while the architectures themselves may be
reused in a new domain, the library of plans typically cannot. One way to
address this problem is to use machine learning techniques to automate the
derivation of planning resources for new domains. In this paper, we apply this
technique to build micro-planning rules for preventative expressions in
instructional text.
\\ (cmp-lg/9607015 , 50kb)
------------------------------------------------------------------------------
\\
Paper: cmp-lg/9607016
From: pereira@research.att.com
Date: Sat, 13 Jul 96 14:35 EDT
Title: Beyond Word N-Grams
Author: Fernando C. N. Pereira (AT&T Research), Yoram Singer (AT&T Research),
Naftali Tishby (Hebrew University)
Comments: 15 pages, one PostScript figure, uses psfig.sty and fullname.sty.
Revised version of a paper in the Proceedings of the Third Workshop on Very
Large Corpora, MIT, 1995
\\
We describe, analyze, and evaluate experimentally a new probabilistic model
for word-sequence prediction in natural language based on prediction suffix
trees (PSTs). By using efficient data structures, we extend the notion of PST
to unbounded vocabularies. We also show how to use a Bayesian approach based on
recursive priors over all possible PSTs to efficiently maintain tree mixtures.
These mixtures have provably and practically better performance than almost any
single model. We evaluate the model on several corpora. The low perplexity
achieved by relatively small PST mixture models suggests that they may be an
advantageous alternative, both theoretically and practically, to the widely
used n-gram models.
\\ (cmp-lg/9607016 , 19kb)
------------------------------------------------------------------------------
\\
Paper: cmp-lg/9607017
From: "Wlodek Zadrozny ((914) 784 7835)" <WLODZ@watson.ibm.com>
Date: Sat, 13 Jul 96 17:31:43 EDT
Title: Natural Language Processing: Structure and Complexity
Author: Wlodek Zadrozny (IBM Research, T. J. Watson Research Center, Yorktown
Heights, NY, USA)
Comments: 8 pp. Latex (documentstyle[ijcai89,named]). In: "Proc. SEKE'96, 8th
Int. Conf. on Software Engineering and Knowledge Engineering", Lake Tahoe,
1996, pages 595-602
\\
We introduce a method for analyzing the complexity of natural language
processing tasks, and for predicting the difficulty new NLP tasks.
Our complexity measures are derived from the Kolmogorov complexity of a
class of automata --- {\it meaning automata}, whose purpose is to extract
relevant pieces of information from sentences. Natural language semantics
is defined only relative to the set of questions an automaton can answer.
The paper shows examples of complexity estimates for various NLP programs
and tasks, and some recipes for complexity management. It positions natural
language processing as a subdomain of software engineering, and lays down
its formal foundation. \\ (cmp-lg/9607017 , 17kb)
%-%-%-%-%-%-%-%-%-%-%-%-%-%-%-%-%-%-%-%-%-%-%-%-%-%-%-%-%-%-%-%-%-%-%-%-%-%-%-
%%--%%--%%--%%--%%--%%--%%--%%--%%--%%--%%--%%--%%--%%--%%--%%--%%--%%--%%--%%
%%%---%%%---%%%---%%%---%%%---%%%---%%%---%%%---%%%---%%%---%%%---%%%---%%%---
******************************************************************************
CMP-LG NEWS
(updated May 14, 1996)
..............................................................................
ACL 96 ON-LINE PROCEEDINGS
An on-line proceedings for ACL 96 is now available courtesy of cmp-lg. The
on-line proceedings provides listings of regular and student session papers,
with links to cmp-lg versions where available, as well as invited lectures and
tutorial abstracts.
ACL 96 authors: The cmp-lg archive is the definitive repository for papers in
computational linguistics. Make sure YOUR paper is available by submitting it
to the archive. You can use the "published" command to add the information
that the paper appears at ACL 96, and it will be added to the on-line
proceedings.
FOR FURTHER INFORMATION
For further information about (among other topics) submission of papers to the
server, subscribing or canceling your subscription, requesting full text of
any of the papers above, retrieving macro files for these papers, searching
past listings, or submitting comments to the server operators, send a message:
To: CMP-LG@XXX.LANL.GOV
Subject: help
or, better yet, access the hypertext help information through the WWW
interface at "http://xxx.lanl.gov/cmp-lg/".
******************************************************************************
This archive was generated by hypermail 2.1.4 : Sat Apr 20 2002 - 15:37:46 EDT