Copy Link
Add to Bookmark
Report
NL-KR Digest Volume 08 No. 55
NL-KR Digest (Fri Nov 8 09:42:28 1991) Volume 8 No. 55
Today's Topics:
lexical database available
Assoc. for Machine Translation Newsletter
3rd Conference on Applied Natural Language Processing
Workshop on Fully-Implemented Natural Language Understanding Systems
Workshop on Natural Language Dialogue Systems
Another Need a text parser question
Submissions: nl-kr@cs.rpi.edu
Requests, policy: nl-kr-request@cs.rpi.edu
Back issues are available from host archive.cssage.rpi.edu [128.113.53.18] in
the files nl-kr/Vxx/Nyy (ie nl-kr/V01/N01 for V1#1), mail requests will
not be promptly satisfied. If you can't reach `cs.rpi.edu' you may want
to use `turing.cs.rpi.edu' instead.
BITNET subscribers: we now have a LISTSERVer for nl-kr.
You may send submissions to NL-KR@RPIECS
and any listserv-style administrative requests to LISTSERV@RPIECS.
-----------------------------------------------------------------
To: nl-kr@cs.rpi.edu
From: btr!public!grady@decwrl.dec.com (Grady Ward grady@btr.com)
Newsgroups: comp.ai.nlang-know-rep
Subject: lexical database available
Date: 3 Nov 91 00:48:59 GMT
Requests for Moby Lexical Database literature
may now be directed to: grady@btr.com
( {decwrl,mips,fernwood}!btr!grady )
Please send your postal address or telephone
(408) 373-1491 if you would like to have the
Moby brochure mailed to you by first-class mail.
------------------------------
To: nl-kr@cs.rpi.edu
Date: Sun, 3 Nov 1991 13:27 MST
From: ECS@yvax.byu.edu
Subject: Assoc. for Machine Translation Newsletter
The International Association for Machine Translation, of which
the Association for Machine Translation in the Americas (AMTA) is a part,
will publish its first newsletter in January 1992 under the general
editorship of John Hutchins in the U.K. Individuals and organizations
in the Americas are invited to send letters, announcements of conferences,
publications or software products, or other material of interest, to the
following address; electronic submissions are encouraged!
Joseph Pentheroudakis
AMTA Newsletter Editor
ECS, Inc.
455 N. University Avenue
Provo, UT 84601
USA
fax: (801) 374-6292
voice: (801) 377-1167
e-mail: pentherj@cc.utah.edu or ecs@yvax.byu.edu
I will be happy to forward announcements from other regions to the
appropriate regional editor.
For information on joining the Association for Machine Translation in
the Americas (AMTA), please contact:
Scott Bennett (fax: 512/471-6084 / voice: 512/471-4166
e-mail: bennett@utxvms.cc.utexas.edu)
Joann Ryan (fax: 301/585-0742 / voice: 301/585-0851)
or
Muriel Vasconcellos (fax: 202/667-8808 / voice: 202/861-4338)
Thanks!
Joseph Pentheroudakis
------------------------------
To: nl-kr@cs.rpi.edu
Date: Wed, 6 Nov 91 11:51:18 -0500
From: walker@flash.bellcore.com (Don Walker)
Subject: 3rd Conference on Applied Natural Language Processing
ANLP-92
3RD CONFERENCE ON APPLIED NATURAL LANGUAGE PROCESSING
Trento, Italy, 1-3 April 1992
sponsored by the
Association for Computational Linguistics
The conference is also supported by the European
Coordinating Committee for Artificial Intelligence
(ECCAI), the Italian Association for Artificial
Intelligence (AI*IA), and Istituto Trentino di
Cultura, Trento.
PURPOSE: The focus of this conference is on the application of
natural language processing techniques to real world problems. It
will include invited and contributed papers, tutorials, an industrial
exhibition, and demonstrations. A special video session is also
being organised. The organizers want the conference to be as
international as possible, and to feature the best applied natural
language work presently available in the world. This conference
follows on from ones held in Santa Monica, California in 1983 and
in Austin, Texas in 1988.
SCIENTIFIC PROGRAM: The program will be sent out early in December
(and will include the application form and the hotel reservation
form). There were about one hundred papers submitted from four
continents. The scientific program will include original papers
solicited in all areas of applied natural language processing,
including: dialog systems; integrated speech and natural language
systems; machine translation; explanation and generation; database
interface systems; tool development; text and message processing;
grammar and style checking; corpus development; knowledge acquisition;
lexicons; language teaching aids; evaluation; adaptive systems;
multilanguage systems; multimedia systems; help systems; and other
applications. Papers will also discuss applications, evaluations,
limitations, and general tools and techniques. The program committee
is co-chaired by Oliviero Stock (IRST) and Madeleine Bates (BBN
Systems & Technologies) and also includes:
Robert Amsler (MITRE) Kathy McKeown (Columbia U)
Giacomo Ferrari (U Pisa) Sergei Nirenburg (Carnegie Mellon U)
Eduard Hovy (USC/ISI) Makoto Nagao (Kyoto U)
Paul Jacobs (General Electric) Remko Scha (U Amsterdam)
Martin Kay (Xerox PARC) Karen Sparck Jones (U Cambridge)
Mark Liberman (U Pennsylvania) Henry Thompson (U Edinburgh)
Paul Martin (IBM) Wolfgang Wahlster (DFKI)
INDUSTRIAL EXHIBITION: The industrial exhibition will feature
products in the usual one-booth-per-company format. For further
information contact:
Gianpietro Carlevaro phone: +39-461-814444
I.R.S.T. fax: +39-461-810851
I-38050 Povo (Trento) ITALY email: carleva@irst.it
To ensure that your requirements are met, you are advised to apply
early. Prices for stands are as follows:
Stand type 1: 9 sqm - Lit. 1800000 + VAT 19% (approx. US$1400)
Stand type 2: 14 sqm - Lit. 2400000 + VAT 19% (approx. US$1900)
DEMONSTRATIONS: One area of the exhibition will be equipped with
SUNs, MACs, and possibly other hardware, and will be available for
informal demonstrations of various applied NL systems. A prize
will be given for the best non-commercial demonstration. Anyone
wishing to present a demo should send a one-page description of
the demo and a specification of the system requirements by 1 December
1991 to:
Carlo Strapparava phone: +39-461-814444
I.R.S.T. fax: +39-461-810851 38050
I-38050 Povo (Trento) ITALY email: strappa@irst.it
TUTORIALS: The meeting will be preceded by one day of tutorials on
31 March 1992 by noted contributors to the field. The program is
being currently defined and will be mailed with the general conference
program. Responsible for tutorials:
Jon Slack phone: +39-461-814444
I.R.S.T. fax: +39-461-810851 38050
I-38050 Povo (Trento) ITALY email: slack@irst.it
FEES: The early registration fee (before February 29, 1992) for
the conference is Lit. 400.000 (approx. US$300). Early student
registration is Lit. 130.000 (approx. US$100). After 29 February
1992 the regular registration fee will be Lit. 500.000 (approx.
US$400), and student registration will be Lit. 200.000 (approx.
US$150). The application form and the hotel reservation form will
be sent out with the program early in December.
WORKSHOPS: The conference will also be preceded by two conference
special workshops, to be held on March 30th. The call for papers
for the two workshops follows. Workshops will admit only a limited
number of participants (about 30 people each) and will cost an
additional fee of Lit. 50.000 (approx. US$40). Please note that
workshop participation is restricted to those registered to the
conference. Requests for information and applications for the
workshops should be directed to the workshop organizers.
GENERAL INFORMATION: Local arrangements are being handled by:
Tullio Grazioli and Oliviero Stock phone: +39-461-814444
I.R.S.T. fax: +39-461-810851
I-38050 Povo (Trento) ITALY email: interne@irst.it
For information on the ACL, contact:
Donald E. Walker (ACL) phone: +1-201-8294312
Bellcore MRE 2A379 fax: +1-201-8295981
445 South Street Box 1910 email: walker@flash.bellcore.com
Morristown, NJ 07960 USA
------------------------------
To: nl-kr@cs.rpi.edu
Date: Wed, 6 Nov 91 11:53:33 -0500
From: walker@flash.bellcore.com (Don Walker)
Subject: Workshop on Fully-Implemented Natural Language Understanding Systems
ANLP-92 Workshop
CALL FOR PARTICIPATION
Trento, Italy, 30 March 1992
FULLY-IMPLEMENTED NATURAL LANGUAGE UNDERSTANDING SYSTEMS
jointly organized by
Kai von Luck (IBM Deutschland),
Claus-Rainer Rollinger (Universitaet Osnabrueck) and
Hans-Joachim Novak (IBM Deutschland)
A large set of theories have been proposed in recent years, covering
one or more aspects of NL understanding systems. Little effort
has been spent on integrating these theories into one system.
Experiments involving the integration of different theories, e.g.
unification-based analysis, DRT-based semantics, logic-based
reasoning, analogical reasoning, and two-level morphology, have
delivered interesting results. One of the major outcomes in this
respect is that the game of ``my component/theory is not responsible
for that task/explanation/problem'' cannot be played any more;
instead a much broader view has to be taken as the deficits of the
theories become apparent. The integration of several theories
explicates their requirements and necessitates their revision.
In this workshop we hope to bring together researchers of different
disciplines within AI natural language understanding systems, e.g.
text understanding systems, dialog systems, knowledge-based machine
translation systems, etc. to discuss the integration problems
emphasizing a holistic view of natural language understanding.
The major result of this workshop is expected to be the exchange
and discussion of known deficits of today's theories that cover
only certain aspects or phases of the NL understanding process as
well as objectively collecting the requirements for these theories.
This effort seems to be promising, as can be observed by the
existence of various experiments underway like, for instance, the
text understanding system LILOG of IBM Germany, as well as by recent
trends as different areas of AI move away from research on only
intrinsic problems of a particular theory towards a more holistic
view of NL understanding. NL systems will only have a future if
our joint efforts are directed towards formulating theories that
can be integrated to a full view of NL understanding.
Researchers of all areas of natural language understanding systems
are invited to actively participate. Contributions should not
cover a particular theory/explanation but rather RESULTS from
integrating different theories into one single system. Reports
which cover limitations of specific theories with respect to
integration and/or concrete demands for the further development
within theories are especially welcome.
Participation in the workshop will be by invitation only, based on
the extended abstracts of the applicants. For reasons of efficiency
the number of participants is limited to a maximum of 30 people.
Agreement of the participants assumed, a compilation of the workshop
and the discussions should be published in 1992 in order to make
the experiences of the participants available to a broad public.
Send 3 to 5 page extended abstracts by surface mail (e-mail copies
are encouraged as well, but a hardcopy is required) no later than
20 January 1992, to the address below:
Hans-Joachim Novak
IBM Deutschland GmbH
WT IWBS, 7000-75
Postfach 80 08 80
D-W-7000 Stuttgart 80, GERMANY
e-mail: novak%ds0lilog.bitnet
Notification of acceptance will be mailed by the end of January 1992.
------------------------------
To: nl-kr@cs.rpi.edu
Date: Wed, 6 Nov 91 11:52:31 -0500
From: walker@flash.bellcore.com (Don Walker)
Subject: Workshop on Natural Language Dialogue Systems
ANLP-92 Workshop
CALL FOR PARTICIPATION
Trento, Italy, 30 March 1992
EMPIRICAL MODELS AND METHODOLOGY FOR NATURAL LANGUAGE DIALOGUE SYSTEMS
jointly organized by
Lars Ahrenberg Nils Dahlback Arne Jonsson
Department of Computer and Information Science
Linkoping University
There is an increasing recognition of the need to put theories and
systems within the field of Natural Language Processing on a firm
empirical ground (cf. the views of the panel on Language Engineering:
The Real Bottleneck of Natural Language Processing at COLING-88).
Researchers on various aspects of discourse, especially, take pains
to base, or at least illustrate, their theoretical developments
with some kind of corpus data. There is quite often a problem,
however, in determining what data are relevant for a specific domain
or application and in deciding what conclusions the data warrant.
In this workshop we want to focus on data used for the design of
natural language interfaces and other dialogue systems accepting
natural language input. In this area we know of three basic sources
for the corpora used: (i) interactions with computers using existing
NLIs, (ii) interactions with computers using simulated NLIs (Wizard
of Oz-studies), and (iii) human-human dialogues collected and/or
analyzed with the purpose of developing computational theories of
discourse.
Several studies of this kind have been published in recent years.
However, the use of these different kinds of corpus data raises a
number of issues in need of clarification, theoretical as well as
methodological: e.g. what are the advantages and disadvantages of
corpora collected with these different methods; what is the
generalizability of the results obtained; what methodological
pitfallss have been found, what means to avoid them, and so on.
Behind many of these questions lies the issue of the extent to
which natural language as used in human-computer interaction is to
be seen as a distinct sublanguage, and to what extent there are
aspects common to all kinds of dialogue.
The workshop will adress both the methodological and the theoretical
issues raised above, but with the focus on the methodological ones.
Its aim is to give active researchers in the field an opportunity
to exchange experiences of and opinions on different
practical/methodological topics such as those mentioned above, and
others. If possible, demonstrations of software for the collection
and analysis of these kind of data will be demonstrated.
Those interested in making a presentation should submit an abstract
of 500-1000 words. The abstract should include a description of
the participant's current research in the area and point to longer
papers on the subject (if available).
Those interested only in participating should submit a statement of
their research interests together with a list of related publications.
Submissions, by e-mail or surface mail, should arrive no later than
20 January 1991 to the address below.
Nils Dahlback
Department of Computer and Information Science
Linkoping University
S-581 83 Linkoping, SWEDEN
email: nda@ida.liu.se
Notification of acceptance will be mailed by the end of January 1992.
------------------------------
To: nl-kr@cs.rpi.edu
Date: Tue, 5 Nov 91 08:12:17 -0500
From: Nancy L. Crowley <ncrowley@galaxy.afit.af.mil>
Subject: Need a text parser
I need a text parser for the front end of my PhD work. It will need to
parse declarative text (no questions or incomplete sentences). The text
is a software specification. I need syntactic information and a
dependency structure because I need to know how the parts of the
sentence relate to each other (such as main noun, modifiers to the
noun, related verb, etc). I am not an expert in NLP - I am a user of
it, so any help would be appreciated.
I can be contacted at ncrowley@galaxy.afit.af.mil.
Nancy Crowley
------------------------------
End of NL-KR Digest
*******************
