Copy Link
Add to Bookmark
Report
NL-KR Digest Volume 13 No. 40
NL-KR Digest Thu Sep 22 08:43:05 PDT 1994 Volume 13 No. 40
Today's Topics:
Position: Speech and NL PhD Studentship at Birmingham
CFP: AAAI SSS 95 Spring Symposium Extending Theories of Action
Announcement: Paper on Neural nets for language translation
Query: prolog for PC
Query: Syntax/Semantics Interface (Object-Oriented Repr.)
Announcement: AAAI SSS 95 LEXICAL KNOWLEDGE, Stanford, Mar 95
Announcement: CMC/95 Cooperative Multimodal Comm., Eindhoven, May 95
Position: Research Posts in Natural Language Engineering, Sheffield
* * *
Subcriptions: listserv-style administrative requests to
nl-kr-request@ai.sunnyside.com.
Submissions, policy, questions: nl-kr@ai.sunnyside.com
Back issues:
FTP: ai.sunnyside.com:/pub/nl-kr/Vxx/Nyyy
/pub/nl-kr/Vxx/INDEX
Gopher: ai.sunnyside.com, Port 70, in directory /pub/nl-kr
Email: write to LISTSERV@AI.SUNNYSIDE.COM, omit subject, mail command:
GET nl-kr nl-kr_file_list
Web: http://ai.sunnyside.com/pub/nl-kr
Editors:
Al Whaley (al@ai.sunnyside.com) and
Chris Welty (weltyc@cs.vassar.edu).
-----------------------------------------------------------------------
From: J.P.Iles@computer-science.birmingham.ac.uk
Date: Fri, 2 Sep 94 14:45:30 BST
To: elsnet-list@cogsci.edinburgh.ac.uk, salt@cstr.edinburgh.ac.uk,
Subject: Position: Speech and NL PhD Studentship at Birmingham
**** PLEASE DISTRIBUTE THIS MESSAGE ***
PhD RESEARCH STUDENTSHIP
SCHOOL OF COMPUTER SCIENCE
THE UNIVERSITY OF BIRMINGHAM
ENGLAND
The School of Computer Science at the University of Birmingham has a
three-year studentship available for EU resident students to work
towards a PhD in
SPEECH AND NATURAL LANGUAGE PROCESSING.
Current work in this topic has focused on the development of a novel
approach to text-to-speech conversion. It is envisaged that future
work will expand the scope of the research to cover cognitive
modelling, with speech recognition being used as a demonstration
application. Relevant papers by William Edmondson and Jon Iles are
included in the further particulars available from the admissions
tutor, or can be obtained from:
ftp://ftp.cs.bham.ac.uk/pub/dist/synth/papers/
http://www.cs.bham.ac.uk/~jpi/papers.html
Dr William Edmondson is keen to extend the work as described above and
we seek a research student who is interested in these topics.
The novelty of the work lies in its use of a processing architecture
which is based on a cognitive model. This is highly parallel and we
expect the successful applicant to tackle issues in software
engineering as well as speech processing and cognitive modelling.
Each studentship covers full registration fees and a contribution
towards living expenses which is equivalent in value to a SERC/EPSRC
research studentship.
For suitably qualified students there will be opportunities to do paid
work helping with teaching or demonstrating.
Applicants will need either a first class or good upper second class
degree, or equivalent. In some cases outstanding MSc performance can
compensate for a lower first degree.
Anyone interested should request application forms and other
information from the Research Student Admissions Tutor:
Dr. Peter Hancox
School of Computer Science,
The University of Birmingham
Edgbaston
Birmingham B15 2TT
England
EMAIL: P.J.Hancox@cs.bham.ac.uk
Phone: +44-(0)21-414-3819
Fax: +44-(0)21-414-4281
-----------------------------------------------------------------------
To: comp-ai-nlang-know-rep@uunet.uu.net
From: cebly@cs.ubc.ca (Craig Boutilier)
Subject: CFP: AAAI SSS 95 Spring Symposium Extending Theories of Action
Date: 5 Sep 1994 07:47:06 -0700
AAAI 1995 Spring Symposium
Extending Theories of Action:
Formal Theory and Practical Applications
March 27--29, 1995, Stanford University
[This document can be found via the URL
http://www.cs.ubc.ca/ftp/local/SSS95/type/CFP.html]
The study of action and its representation has played a central role
in AI, and numerous theories of action have been studied within
different subdisciplines of AI research, as well as other areas. The
research focus in these different areas --- among them knowledge
representation, planning, reasoning under uncertainty, control theory
and decision theory --- has often been motivated by different issues
and types of problems, or based on different underlying assumptions.
Theories of action proposed within the KR community typically address
compact representations and associated problems (such as the frame,
qualification and ramification problems). The aim is often to provide
natural and concise methods for specifying system dynamics. Similar
motivations but very different methods are used by researchers in
uncertainty, where the use of influence diagrams and belief networks
are the norm. In contrast, planning systems usually rely on
representations that can be more easily exploited by planners in a
computationally manageable fashion. In control and decision theory,
while actions play a key role, the question of compact representation
of actions is seldom addressed, the focus directed to reasoning about
the effects of actions in small state spaces. However, the types of
actions and domains dealt with in control and decision theory are
often more general than those discussed in KR and (classical) planning,
allowing actions with uncertain and partially-observable effects.
The assumptions made and reasoning methods adopted when putting theories
of action into practice are also often quite different. In many control
and decision problems, search through small state spaces is used or
analytical, closed-form solutions are sought, while in planning, search
methods over the space of partially-ordered plans are frequently used.
In the uncertainty community the emphasis in both theory and practice is
on the exploitation of problem structure (as embodied in network
representations) for computational adavantage.
This symposium is intended to bring together researchers in diverse
fields of AI, including both theoreticians and practitioners. The aim
is to assess the state of the art, discuss common foundations of action
representation and reasoning, explore future directions in which
current theories of action must be extended, and identify critical
questions for the successful application of action theories.
The technical focus of the proposed symposium will be twofold: evaluating
the current state of the art, especially identifying the underlying
issues that drive research in different fields and characterizing the
common and distinguishing concerns within these fields; and identifying
relevant research issues for both the advancement of the state of the art
and the incorporation of these advances into systems and applications. We
invite contributions addressing all aspects of representing and reasoning
about action. Specific topics include, but are not limited to:
* Characterizing and evaluating existing approaches.
What are the key issues addressed by specific theories of action?
To what extent do current systems successfully solve the central
problems? What are the strengths and weaknesses of "current"
representations? How can models used in one area be used in others?
Are there appropriate common models (e.g., state transition
models)? How do specific representions relate to these models?
How can compact actions representations be exploited computationally?
* Technical issues in extending theories of actions.
What capabilities should theories of action provide?
What is required to incorporate the following considerations in
our theories: Nondeterminism; default/probabilistic effects and
qualifications; Exogenous events; Nonprimitive actions (sequences,
programs); Concurrent actions; Explicit representation of time;
Costs and other notions from utility theory.
* Putting Theories of Action into Practice
How can the gap between theory and practice be narrowed? What
compromises are necessary? How and to what extent should
implementation considerations influence the formulation of theories
of action? What are possible near- and long-term applications and
their specific needs? What are appropriate measures of success?
We invite extended abstracts (max. five pages) of two sorts:
- Technical papers addressing issues or proposing methods for
representing or reasoning about action (especially contributions
that draw from or bring together different approaches). Reports on
work in progress are welcome.
- Position papers advocating particular approaches or steps toward
integrating ideas from different communities
Others interested in attending should submit a statement of interest
(max. two pages) describing his or her research on relevant problems.
Electronic submissions are strongly encouraged and should be sent to
action@cs.ubc.ca. Paper submissions should be sent to
Craig Boutilier
Department of Computer Science
University of British Columbia
Vancouver, British Columbia
CANADA, V6T 1Z4
cebly@cs.ubc.ca
Inquiries should be directed to either co-chair.
Organizing Committee: Craig Boutilier (co-chair), University of
British Columbia, cebly@cs.ubc.ca; Tom Dean, Brown University;
Mois\'{e}s Goldszmidt (co-chair), Rockwell, moises@rpal.rockwell.com;
Steve Hanks, University of Washington; David Heckerman, Microsoft;
Ray Reiter; University of Toronto
Submissions Due: October 28, 1994
Notification/Invitations: November 30, 1994
Final Material for Working Notes Due: January 20, 1995
Symposuim Dates: March 27--29, 1995
-----------------------------------------------------------------------
To: comp-ai-nlang-know-rep@uunet.uu.net
From: nk3@doc.ic.ac.uk (Nenad Koncar)
Subject: Announcement: Paper on Neural nets for language translation
Date: 6 Sep 94 14:04:22 GMT
NEW PAPER AVAILABLE :
A paper on natural language translation using neural networks is available at
our local archive, and at the neuroprose archive.
The abstract and information for obtaining the paper follow :
= = = = = = = = = = = = = = = ===
A Natural Language Translation Neural Network
Nenad KONCAR
Imperial College of Science, Technology and Medicine, London, UK
N.Koncar@doc.ic.ac.uk
Dr. Gregory GUTHRIE
Maharishi International University, Fairfield, Iowa, USA
guthrie@miu.edu
Abstract
We have tested the ability of neural networks to perform natural language
translation. Our results have shown a greatly improved translation accuracy in
comparison to the work of R.B. Allen (1987) in translating English into
Spanish. A neural network was trained on a set of 10,000 sentences from a
total of 24,750 sentences using a novel training algorithm. On a test set of
100 sentences the neural network showed a 98% sentence accuracy. The neural
network had 48 input nodes, 70 nodes in the first hidden layer, 1 node in the
third hidden layer, and 36 nodes in the output layer (48-70-1-36). A fully
connected architecture was used.
= = = = = = = = = = = = = = = ===
Full reference:
Koncar, N., Guthrie, G. "A Natural Language Translation Neural Network".
International Conference on New Methods in Language Processing (NeMLaP),
Centre for Computational Linguistics, UMIST, Manchester, United Kingdom,
14-16th September, 1994.
= = = = = = = = = = = = = = = ===
To retrieve paper :
ftp dolphin.doc.ic.ac.uk
login : anonymous
password : <youremail@site>
cd /pub/papers
hash
bin
get <paper title>
bye
- - - - - - - - - - - - - - - ---
Also retrievable from : archive.cis.ohio-state.edu
neuroprose archive. (also via anonymous ftp )
All comments and suggestions would be welcome.
Nenad Koncar
--
Nenad Koncar email: N.Koncar@doc.ic.ac.uk
Dept. of Computing, Imperial College tel. : +44-(0)71-594-8341
180 Queen's Gate fax. : +44-(0)71-244-8397
London SW7 2BZ, United Kingdom Room : 346 Huxley
-----------------------------------------------------------------------
From: theriaal@ere.umontreal.ca
Subject: Query: prolog for PC
Date: Wed, 7 Sep 1994 12:35:23 GMT
Hello
I am looking of a PC version of the PROLOG program.
If any one can let me know the ftp site where it could be optained (if it
exists) please. email me at:
theriaal@ere.umontreal.ca
Thank You
Alain Theriault
Departement de linguistique et de traduction
Universite de Montreal
-----------------------------------------------------------------------
From: Joachim Quantz <jjq@cs.tu-berlin.de>
Date: Thu, 8 Sep 1994 12:06:59 +0200
To: nl-kr@ai.sunnyside.com
Subject: Query: Syntax/Semantics Interface (Object-Oriented Repr.)
I have two related questions on the interface between
syntactic parsing and subsequent modules (e.g. semantics,
pragmatics) in NLP systems.
I assume that the output of a syntactic parser will be something
like a phrase structure tree. It seems that in most existing systems
the semantic module takes this phrase structure tree as input and
PARSES it in order to build up a semantic representation.
1. Are there any systems (or is there any theoretical work), in which
the phrase structure tree is treated as an abstract data type for
which access predicates are provided?
I would be especially interested in syntactic representations which
treat the nodes in the phrase structure trees (i.e. the words and
phrases) in an object-centered way. `Functional predicates' would then
return, for example,
- the subject of a sentence
- the daughters of a phrase
- the topic of a sentence
- the direct object of a verb
- the preposition of a prepositional phrase
- the case of a noun phrase
- etc.
Obviously, which predicates are applicable at a specific object (node)
depends on the type of the object (e.g. sentence, noun phrase, verb).
(I know that it is in principle possible to build such an interface
on top of, for example, an HPSG-like feature structure. I'd be interested
to know whether this has ACTUALLY been done already.)
2. If such interfaces exist, are they designed for a specific syntactic
theory, or can they be used for several different syntactic theories?
Alternatively, is there any work concerned with identifying linguistic
relations (as exemplified by the ones above) which are used in
several/many/most/all syntactic theories?
I have already been referred to work by
a) Randy Goebel, Dekang Lin (University of Alberta, Canada)
(Could anyone send me their e-mail addresses)
b) Manfred Pinkal, Sebastian Millies (University Saarbruecken, Germany)
Thanks for any information on this,
Joachim Quantz
| . . __ | J. Joachim Quantz | jjq@cs.tu-berlin.de |
| /| /| | | | TU Berlin, FR 5-12 | phone: |
| / |/ |/|__| | Projekt KIT-VM11 | +49 30 314 254 94 |
| /| /| _|_ | Franklinstr. 28/29 | fax: |
| \| \| | | D-10587 Berlin | +49 30 314 249 29 |
-----------------------------------------------------------------------
Date: Wed, 14 Sep 1994 11:45:54 -0400
From: Judith Klavans <klavans@cs.columbia.edu>
To: dg@ai.uga.edu, lantra-l%finhutc.BITNET@cuvmb.cc.columbia.edu,
Subject: Announcement: AAAI SSS 95 LEXICAL KNOWLEDGE, Stanford, Mar 95
* * * * *** Call for Participation * * * * * ***
REPRESENTATION AND ACQUISITION OF LEXICAL KNOWLEDGE: POLYSEMY, AMBIGUITY, AND GENERATIVITY
1995 AAAAI Spring Symposium Series
Stanford University, California
March 27 - 29, 1995
Chair: Judith L. Klavans, Columbia University
Committee: Branimir K. Boguraev, Apple Computer
Lori S. Levin, Carnegie Mellon University
James Pustejovsky, Brandeis University
The lexicon is at the core of many NL, IR, and KR systems, and thus
can play a central role in determining the success or failure of the
endeavor. Nonetheless, points of sharp controversy have arisen
concerning the most flexible and powerful way to represent the
extensive variety of lexical information required to drive robust
applications. We intend this symposium to provide a forum to discuss
problematic issues of lexical representation, and ways to solve
difficult and complex questions.
Despite the fact that the need for a common lexicon has been a recent
research focus, there is no general agreement on a lexical
representation that is both complete enough for specification of even
basic syntactic environments, and flexible enough to handle the
productivity and underspecification that are required for representing
lexical semantics. The focus of the symposium will be on ways to
determine the optimal representation of lexical knowledge needed for
flexible broad-coverage lexicons, as well on the acquisition of that
knowledge.
Relevant interest areas include: Natural language processing,
Information Retrieval, Knowledge Representation, Cognitive Science,
Psychology, Philosophy, and others. Those wishing to attend without
presenting should submit a brief description of their research
interests and opinions, and a list of relevant publications.
The symposium will maintain a balance between theoretical and
applications oriented papers. Authors should identify precisely how
the paper is relevant to the topic, what specific problems are
addressed, and a clear statement of what solutions are proposed.
Well-grounded controversial positions are encouraged.
A number of panels and invited talks are being planned to review
where the field is moving in the future, keeping in mind a historical
perspective on where we have been, where we have succeeded, and
where we have failed.
Authors should submit extended abstracts of up to 2000 words in
12-point font electronically by October 28, 1994, with a hard-copy
backup to:
Dr. Judith L. Klavans
AAAI Symposium Chair
Columbia University
Department of Computer Science
500 W 120th Street
New York, NY 10027, USA
phone: 212-939-7120
fax: 914-478-1802
e-mail: klavans@cs.columbia.edu
Sponsored by the American Association for Artificial Intelligence
445 Burgess Drive
Menlo Park, CA 94025
(415) 328-3123
sss@aaai.org
-----------------------------------------------------------------------
From: Harry.Bunt@kub.nl (Harry C. Bunt, ITK)
Date: Fri, 16 Sep 1994 16:32:46 +0200
To: rjbeun@prl.philips.nl, wsinrpn@info.win.tue.nl, M.Wagemans@kub.nl,
Subject: Announcement: CMC/95 Cooperative Multimodal Comm., Eindhoven, May 95
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
CMC/95
International Conference on Cooperative Multimodal Communication,
Theory and Applications
* ****
Sponsored by the Universities of Brabant
Joint Research Organization (SOBU)
Eindhoven, The Netherlands, 24-26 May 1995
* ****
FIRST ANNOUNCEMENT AND CALL FOR PAPERS
* ****
The Technical University Eindhoven, in collaboration with the
Institute for Perception Research in Eindhoven and the Institute for
Language Technology and Artificial Intelligence in Tilburg, will host
an international conference on the theory and applications of
COOPERATIVE MULTIMODAL COMMUNICATION
to take place in Eindhoven, The Netherlands, 24-26 May 1995.
The aim of the conference is to bring together scientists involved
in research concerning the design, implementation, and application of
forms of cooperative human-computer communication where natural language
(typed or spoken) is used in combination with other modalities, such as
visual feedback and direct manipulation.
TOPICS OF INTEREST
* ****
The conference will focus on formal, computational, and user aspects
of building cooperative multimodal dialogue systems. Papers are sought
in areas which include, but are not limited to, the following topics:
* cooperativity in multimodal dialogue
* natural language semantics in a multimodal context
* formal and computational models of dialogue context
* incremental knowledge representation and dialogue
* interacting with visual domain representations
* collaborative problem solving
* constraint-based approaches to animation and visual modelling
* effective use of different interactive modalities
* modelling temporal aspects of multimodal communication
* type theory and natural language interpretation
* knowledge sharing technologies
All submitted papers will be refereed by an international programme
committee.
SUBMISSION REQUIREMENTS
* ****
Authors are asked to submit an extended abstract of their paper of
minimally 4 and maximally 7 pages, including references and keywords,
by December 15, 1994. Only electronical submission will be possible.
Submitted extended abstracts should be emailed to denk@kub.nl; they
should preferably be in standard LaTeX format.
If, for whatever reason, electronic submission is not possible, please
contact the organization committee secretariat (phone +31-13.66.23.80,
fax +13 - 13.66.29.48).
IMPORTANT DATES
* ****
Submission of extended abstracts 15 December, 1994
Notification of acceptance 1 February, 1995
Final papers due 15 March, 1995
ORGANIZATION
* *
Programme Committee: Harry Bunt (Tilburg) (chair)
Norman Badler (Pittsburgh)
Jeroen Groenendijk (Amsterdam)
Walther von Hahn (Hamburg)
Dieter Huber (Mainz)
Hans Kamp (Stuttgart) (*)
John Lee (Edinburgh)
Joseph Mariani (Parijs)
Mark Maybury (Cambridge MA)
Paul McKevitt (Sheffield)
Rob Nederpelt (Eindhoven)
Kees van Overveld (Eindhoven)
Ray Perrault (Stanford)
Donia Scott (Brighton) (*)
Wolfgang Wahlster (Saarbruecken)
Bonnie Webber (Philadelphia)
Kent Wittenburg (Morristown NJ) (*)
(*): to be confirmed
Organization Committee: Robbert-Jan Beun (chair)
Tijn Borghuis
Harry Bunt
Rob Nederpelt
Marianne Wagemans
FURTHER INFORMATION
* *
CMC/95 is scheduled to take place on Wednesday, Thursday, and Friday
in 1995, week 21. These dates have been chosen in view of the fact
that two other, somewhat related conferences will take place elsewhere
in Europe between Monday, May 29 and Saturday, June 3; one in
Montpellier, France (on virtual reality and human-computer
interaction), and one in Hanstholm, Denmark (on spoken dialogue
systems). It will thus be possible to combine participation in CMC/95
with that of (one of) the other conferences.
The participation fee for CMC/95 is expected to be around Dfl 250, or
$ 150. Registration information will be provided in the forthcoming
Call for Participation.
Further information: For questions concerning the scientific content:
Harry Bunt
ITK
Tilburg University
P.O. Box 90153, 5000 LE Tilburg
Phone +31 - 13.66.30.60, fax +31-13.66.25.37
email: Harry.Bunt@kub.nl
For questions concerning the organization:
Robbert-Jan Beun
IPO
P.O. Box 513, 5600 MB Eindhoven
Phone +31 - 40.77.38.73, fax +31 - 40.77.38.76
email: rjbeun@prl.philips.nl
For general questions:
SOBU
Tilburg University
P.O. Box 90153, 5000 LE Tilburg
Phone +31-13.66.23.80, fax +13 - 13.66.29.48.
email: denk@kub.nl
Via WorldWideWeb: http://itkwww.kub.nl:2080/itk/Docs/DenK.html.
--
***--*--*---------------------- Harry C. Bunt ----------------------------+
** * * KUB-University Tilburg, the Netherlands Phone: (+31) 13 663060|
* * * bunt@kub.nl |
+-*--*----------------------------- ITK ---------------------------------+
-----------------------------------------------------------------------
Date: Tue, 20 Sep 94 13:08:50 BST
From: Yorick Wilks <yorick@dcs.shef.ac.uk>
Subject: Position: Research Posts in Natural Language Engineering, Sheffield
To: Sigart@logkon.arpa, aaai@sumex-aim.stanford.edu, aisb@cogs.sussex.ac.uk,
Please post
= = = = = = = = = = = = = = = =
The University of Sheffield
Department of Computer Science
TWO RESEARCH POSTS IN
NATURAL LANGUAGE ENGINEERING
Two research associate posts are available in the Natural Language research
group from January 1995. These posts are associated with a grant from the
UK Engineering and Physical Science Research Council on 'Large Scale
Information Extraction from Text'. Both appointments will be for 36 months.
Post 1: The candidate will be involved in the development of a general
architecture for text extraction (GATE) which will support the integration,
testing, and enhancement of existing language processing components to produce
evaluable information extraction systems. The candidate should have a strong
background in computational linguistics or artificial intelligence, including
good programming skills, and should have a PhD or equivalent research
experience in a relevant area. The post will be on the UK RA1A scale, with a
starting salary of around 15K pounds p/a.
Post 2: The candidate will be required to liaise with UK and international
research sites to obtain, install and evaluate language processing components,
corpora, and lexical resources in the context of GATE. The candidate should
have a good degree in computer science or related area, with knowledge of
computational linguistics and should have good Unix/Internet skills. The post
will be on the UK RA1B scale, with a starting salary of around 13K pounds p/a.
The candidate may have the opportunity to register for a PhD.
Informal enquiries to Yorick Wilks (y.wilks@dcs.shef.ac.uk) or Rob Gaizauskas
(r.gaizauskas@dcs.shef.ac.uk).
Further particulars from:
Director of Human Resource Management,
The University of Sheffield,
Western Bank,
Sheffield S10 2TN
Tel: +44 (0)742 824144
Closing date for applications: 15 October 1994. Ref: B2321.
An Equal Opportunity Employer
End of NL-KR Digest
*******************
