Copy Link
Add to Bookmark
Report
NL-KR Digest Volume 06 No. 40
NL-KR Digest (Tue Oct 31 09:37:40 1989) Volume 6 No. 40
Today's Topics:
discourse and anaphora
Speech Processing Systems for Sanskrit language
SNAP/NLP at USC
Prolog parser
More papers on connectionism and natural language
CALL FOR PAPERS - CONNECTION SCIENCE: Special Issue
SPECIAL CSLI LECTURE BY DOUG HOFSTADTER ON 13 NOVEMBER
Recent Memoranda in Computer and Cognitive Science (NLP only)
NATO Workshop announcement
Submissions: nl-kr@cs.rpi.edu
Requests, policy: nl-kr-request@cs.rpi.edu
Back issues are available from host archive.cs.rpi.edu [128.213.1.10] 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.
[[ I screwed up again and skipped issue 38, so there was none ]]
-----------------------------------------------------------------
To: nl-kr@cs.rpi.edu
Date: Thu, 5 Oct 89 09:52:48 -0400
From: rapaport@cs.Buffalo.EDU (William J. Rapaport)
Subject: discourse and anaphora
If you'll send me your US mail address, I'll send you a copy of:
Li, Naicong (1986), "Pronoun Resolution in SNePS," SNeRG Technical Note
No. 18 (Buffalo: SUNY Buffalo Department of Computer Science, SNePS
Research Group).
William J. Rapaport
Associate Professor of Computer Science
Interim Director, Center for Cognitive Science
Dept. of Computer Science||internet: rapaport@cs.buffalo.edu
SUNY Buffalo ||bitnet: rapaport@sunybcs.bitnet
Buffalo, NY 14260 ||uucp: {decvax,watmath,rutgers}!sunybcs!rapaport
(716) 636-3193, 3180 ||fax: (716) 636-3464
------------------------------
To: nl-kr@cs.rpi.edu
From: Ranga.Vemuri@UC.EDU (Dr. Ranga R. Vemuri)
Newsgroups: comp.ai.nlang-know-rep,soc.culture.indian
Subject: Speech Processing Systems for Sanskrit language
Date: 9 Oct 89 17:15:54 GMT
Followup-To: ranga@uceng.uc.edu
Are there any speech processing systems for the Sanskrit language
(or for any other phoneticallly sound Indian languages) ?
Any information is appreciated. Thanks.
Ranga.
ranga@uceng.uc.edu
------------------------------
To: nl-kr@cs.rpi.edu
Date: Sun, 29 Oct 89 10:00:46 PST
From: demara%gringo.usc.edu@usc.edu (Ron DeMara)
Subject: SNAP/NLP at USC
Newsgroups: comp.ai.nlang-know-rep
Our group in the EE-Systems department at USC is working on the design
of a prototype natural language processing system called SNAP/NLP. The
objective of SNAP/NLP is to provide an experimental system that utilizes
the inherent parallelism of the Semantic Network Array Processor (SNAP)
for text understanding and question answering. SNAP is a marker passing
hardware architecture for knowledge processing that is also in
development at USC. SNAP/NLP will be an integrated set of software containing
a syntactic parser, semantic interpreter, discourse analyzer and a classifier.
We would like to know about the availability of Augmented Transition Network
(ATN) parsers in the public domain. We are looking for an existing ATN based
parser for English text, preferably implemented in LISP. We would appreciate
any pointers to what may be available. Thank you.
Ron DeMara, demara@gringo.usc.edu
------------------------------
To: nl-kr@cs.rpi.edu
Date: Sat, 30 Sep 89 16:48:58 CDT
From: Jan Wilms <JWILMS%MSSTATE.BITNET@CORNELLC.cit.cornell.edu>
Subject: Prolog parser
Does anyone on the net have access to a public domain natural
language parser in PROLOG? The intended target machine is a
Symbolics workstation. I am especially looking for a chart
parser, but any non-trivial parser is welcome.
Thanks in advance
G. Jan WILMS
JWILMS@MSSTATE
POBox 1715 MSU, MS 39762
(601) 323 5462
------------------------------
To: nl-kr@cs.rpi.edu
Date: Wed, 20 Sep 89 08:34:41 EDT
From: rba@flash.bellcore.com (Robert B Allen)
Subject: More papers on connectionism and natural language
Allen, R.B. & Riecken, M.E. (1989). Reference in connectionist language
users. Connectionism in Perspective, R. Pfeifer, Z. Schreter, F.
Fogelman-Soulie, and L. Steels (eds.). Elsevier: Amsterdam, 301-308.
(presented at Connectionism in Perspective, Zurich, Oct. 1988).
Allen, R.B., & Riecken, M.E. (Sept. 1988). Interacting and communicating
connectionist agents. Proceedings of the International Neural Network So-
ciety. 67. Boston.
Riecken, M.E. (Nov. 1988). Neural networks in natural language processing
and distributed artificial intelligence. Thesis presented to the Depart-
ment of Computer and Electrical Engineering, University of New Mexico.
Allen, R.B. (Nov. 1989). Developing agent models with a neural reinforce-
ment technique. IEEE Systems Man and Cybernetics Conference. Cambridge,
MA.
Allen, R.B. (Aug. 1988). Sequential connectionist networks for answering
simple questions about a microworld. Proceedings of the Cognitive Science
Society. 489-495. Montreal.
Hanson, S.J., & Kegl, J. (Aug. 1987). PARSNIP: A connectionist network
that learns natural language grammar from exposure to natural language sen-
tences. Proceedings of the Cognitive Science Society. Seattle, WA. 106-
119.
Allen, R.B. (June 1987). Several studies on back-propagation and natural
language. Proceedings of the International Conference on Neural Networks.
San Diego, II/335-341.
Allen, R.B., & Kaufman, S.M. (Oct. 1989). Identifying and discriminating
temporal events with connectionist language users. IEE Conference on Ar-
tificial Neural Networks, London.
Allen, R.B. (June, 1989). Sequence generation with connectionist state
machines. International Joint Conference on Neural Networks. Washington,
2/593.
Allen, R.B. (Feb. 1989). Adaptive training and connectionist state
machines. ACM Computer Science Conference. Louisville, 428.
------------------------------
To: nl-kr@cs.rpi.edu
Date: Fri, 29 Sep 89 07:43:42 EDT
From: rba@flash.bellcore.com (Robert B Allen)
Subject: CALL FOR PAPERS - CONNECTION SCIENCE: Special Issue
(Journal of Neural Computing, Artificial Intelligence and Cognitive Research)
CONNECTIONIST RESEARCH ON NATURAL LANGUAGE
Editor: Noel E. Sharkey, University of Exeter
Special Editorial Review Panel
Robert Allen, Bellcore, New Jersey
Garrison W. Cottrell, University of California, San Diego
Michael G. Dyer, University of California, Los Angeles
Jeffrey L. Elman, University of California, San Diego
George Lakoff, University of California, Berkeley
Wendy W. Lehnert, University of Massachusetts at Amherst
Jordan Pollack, Ohio State University
Ronan Reilly, Beckmann Institute, Illinois
Bart Selman, University of Toronto
Paul Smolensky, University of Colorado, Boulder
This special issue will accept submissions of full length connectionist papers
and brief reports from any area of natural language research including:
Connectionist applications to AI problems in natural
language (e.g. paraphrase, summarisation, question answering).
New formalisms or algorithms for natural language processing.
Simulations of psychological data.
Memory modules or inference mechanisms to support natural
language processing.
Representational methods for natural language.
Techniques for ambiguity resolution.
Parsing.
Speech recognition, production, and processing.
Connectionist approaches to linguistics (phonology, morphology etc.).
Submissions of short reports or recent updates will also be accepted for
the Brief Reports section in the journal. No paper should be currently
submitted elsewhere.
DEADLINES:
Deadline for submissions: December 15th 1989
Decision/reviews by: February 1990
Papers may be accepted to appear in regular issues if there is insufficient
space in the special issue.
For further information about the journal please contact:
Lyn Shackleton
(Assistant Editor)
Centre for Connection Science JANET: lyn@uk.ac.exeter.cs
Dept. Computer Science
University of Exeter UUCP: !ukc!expya!lyn
Exeter EX4 4PT
Devon, U.K. BITNET: lyn@cs.exeter.ac.uk@UKACRL
------------------------------
To: nl-kr@cs.rpi.edu
Date: Fri, 27 Oct 89 16:28:59 PDT
From: ingrid@russell.Stanford.EDU (Ingrid Deiwiks)
Subject: SPECIAL CSLI LECTURE BY DOUG HOFSTADTER ON 13 NOVEMBER
CONCEPT ACQUISITION
(Tentative Title)
Doug Hofstadter
Departments of Computer Science and Psychology
University of Michigan
presently visiting scholar at
San Francisco State University
Doug Hofstadter will give a special lecture at CSLI on Monday, 13
November 1989, at 1:15, in Cordura 100. Abstract to follow.
------------------------------
To: nl-kr@cs.rpi.edu
From: yorick@NMSU.Edu
Date: Tue, 10 Oct 89 19:34:41 MDT
Subject: Recent Memoranda in Computer and Cognitive Science (NLP only)
For copies of the technical reports listed below write to:
Memoranda Series
Computing Research Laboratory
Box 30001
New Mexico State University
Las Cruces, New Mexico 88003
USA
Fowler, R.H., Slator, B.M. & Balogh, I. (1989),
On Psychological Plausibility in Artificial Intelligence, CRL,
MCCS-89-150.
The Artificial Intelligence literature is liberally laced with claims
about cognitive reality. Sometimes these are strong claims that cite
empirical psychological evidence; but more often these claims take the
form of weak appeals to ``psychological plausibility.'' To examine the
nature and scientific status of these claims, AI research is characterized
along a particular dimension, cast as the ``psychological evidence line.''
Then, some ideas about theory in AI are examined, especially the thorny
notion of ``models'' in AI theories: what does it mean to use human
intellect as a model in an AI theory, or in an AI program? Then, as is so
often the case, further light is shed by an historical characterization,
giving evidence for a particular grouping of
``camps'' in AI, according to how psychological evidence ``matters'' to
them. These discussions set the scene, finally, for an examination of the
role (really, roles) that psychological plausibility actually plays in AI;
and this leads naturally into a discussion, and some conclusions, about
which of these roles are appropriate, and which are not.
Barnden, J. (1989),
Neural-Net Implementation of Complex Symbol-Processing in a Mental
Model Approach to Syllogistic Reasoning, CRL, MCCS-89-154.
A neural net system called ``Conposit'' is described. Conposit
performs rule-based manipulation of very short term, complex symbolic
data structures. This paper concentrates on a simulated version of
Conposit that embodies core aspects of Johnson-Laird's mental model
theory of syllogistic reasoning. This Conposit version is not
intended to be a psychological theory, but rather to act as a test and
demonstration of the power and flexibility of Conposit's unusual
connectionist techniques for encoding the structure of data.
Barnden, J. (1989),
Belief, Metaphorically Speaking*, CRL, MCCS-89-155.
The central claim of the paper concerns AI systems that attempt to
represent propositional attitudes in realistic situations, and
particularly in situations portrayed in natural language discourse.
The claim is that the system, in order to achieve a coherent, useful
view of a situation, must often ascribe, to outer agents, views of
inner agents' attitudes that are based on rich explications in terms
of commonsense metaphorical views of mind. This elevates the
emasculated metaphors based on notions of world, situation, container,
and so on that underlie propositional attitude representation
proposals to the status of explicitly-used, rich metaphors. A system
can adopt different patterns of commonsense inference about attitudes
by choosing different metaphors. The current stage of development of
a detailed representation scheme based on the claim is described. The
scheme allows different metaphors to be used for the explication of
attitudes at different levels in a nested-attitude situation.
Guo. C-M. (1989),
Constructing A Machine Tractable Dictionary From Longman Dictionary of
Contemporary English, CRL, MCCS-89-156.
Dissertation.
It is the purpose of this research to design a machine-tractable
dictionary (henceforth MTD) from Longman Dictionary of Contemporary
English (henceforth LDOCE). The MTD is intended to be a basic
facility for a whole spectrum of natural language processing tasks.
The research adopts a compositional-reduction approach to obtain a
formalized set of definitions of sense entries in a nested predicate
form, where the predicates are a set of "seed sense". The focus of
this research is on the derivation of these "seed senses" and their
utilization in the construction of the MTD.
The Construction of the proposed MTD involves the following four
steps: Step: Determine the "defining senses" of LDOCE, i.e., those
world senses that are used in the definition of the meaning of 2,137
``controlled words'' of LDOCE, step 2: Derive the ``seed senses'' of
LDOCE. The ``seed senses" are a subset of the defining sense which
are sufficient to define senses of Step 1. The seen senses are taken
as a natural set semantic primitives derived from LDOCE; step 3:
Hand-code the initial knowledge base for the natural set of semantic
primitives derived from LDOCE; step 4: Construct a MTD for the
controlled words and the rest of LDOCE words by means of bootstrapping
process is a process of knowledge acquisition from dictionary definition
text.
Step 1 of the construction process has been completed. A total of
3,860 defining senses have been determined. Step 2 of the
construction process has also been completed. A total of 3,280 word
senses are found to be the seed senses of LDOCE. These seed senses
are taken as a natural set of semantic primitives derived from the
dictionary. The feasibility of Steps 3 and 4 of the coprocess have
been demonstrated with implemented examples. What
remains to be accomplished is to complete Steps 3 and 4 to build a
full-sized MTD from LDOCE using as guidelines the results of initial
implementation of the two steps.
------------------------------
To: nl-kr@cs.rpi.edu
Date: 30 Oct 89 11:37:00 EDT
From: "SWARTZ, MERRYANNA" <swartz@alexandria-emh2.army.mil>
Subject: NATO Workshop announcement
Please post the following:
A NATO ADVANCED WORKSHOP ON
INTELLIGENT TUTORING SYSTEMS (ITS) FOR FOREIGN LANGUAGE LEARNING
September 19-21, 1990
Washington, D.C.
USA
Focus of the Workshop: To broaden technological advancements in foreign
language ITS applications. To exchange and synthesize scientific progress
in four technical areas: computational bases for foreign langauge ITS,
modelling and diagnosis of the language student, tutorial strategies and
learner control, and hypermedia for interface design.
Background: Language is a "bridge to international communication." As
the international community grows smaller and smaller in economic, scientific,
and day-to-day exchanges, multilingualism becomes a vital skill. Teaching
language skills so that they are easily acquired and retained poses a challenge
to educational and computational researchers. One solution is to create an
intelligent tutoring system for language learning. But how can we build such
an environment? What computational resources are needed? What tutoring
strategies will be used? How will diagnosis and student modelling be
accomplished? What kind of interface is best for presenting language to
students? Current advances in artificial intelligence and natural language
processing technology provide a unique opportunity for developing ITS to
support foreign lanaguage learning that goes beyond grammar instruction.
This workshop will discuss issues in each of the four topic areas and
provide possible solutions to some of the research problems we face.
Participants: Researchers from computer science, foreign language and
linguistics, and psychology who are are interested should submit a brief
abstract of their work (500 words) by January 1990. Demonstrations of
systems,prototypes are welcomed. Submitted abstracts will be reviewed by
the organizing committee by March 1990.
For more information contact:
Merryanna L. Swartz (PERI-IC)
US Army Research Institute
5001 Eisenhower Ave.
Alexandria, VA 22333
USA
phone: (202)274-5569/40, email: swartz@alexandria-emh2.army.mil
Organizing committee: Merryanna L. Swartz, Masoud Yazdani, Joseph
Psotka, Henry Hamburger, Gerard Kempen
------------------------------
End of NL-KR Digest
*******************
