Copy Link
Add to Bookmark
Report
NL-KR Digest Volume 15 No. 22
NL-KR Digest Tue May 14 07:30:01 PDT 1996 Volume 15 No. 22
Today's Topics:
CFP: ESSLLI'96 Student Session, Aug 96, Prague
Query: German Grammar Checking Feasibility
CFP: ESSLLI'96 Robust Parsing Wkshp, Aug 96, Prague
Announcement: PRICAI-96 Pac. Rim AI Conf., Aug 96, Cairns
Announcement: ILLC Logic Course via the Internet, Amsterdam
Announcement: MULSAIC'96 Multiling. S/W Wkshp, Aug 96, Budapest
Announcement: Report on Hybrid Systems, R. Sun, Alabama
* * *
Subcriptions: listserv-style administrative requests to
nl-kr-request@ai.sunnyside.com.
Submissions, policy, questions: nl-kr@ai.sunnyside.com
To speed up processing of your submission write to
listserv@ai.sunnyside.com with the message:
GET nl-kr style
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@sigart.acm.org).
-----------------------------------------------------------------------
Date: Wed, 17 Apr 1996 15:07:46 +0200 (MET DST)
From: Anne-Marie Mineur <mineur@CoLi.Uni-SB.DE>
To: hpsg@ling.ohio-state.edu, Sigparse-List@cs.cmu.edu,
Subject: CFP: ESSLLI'96 Student Session, Aug 96, Prague
** Please distribute among your colleagues and students! **
THE ESSLLI'96 STUDENT SESSION
CALL FOR PAPERS
Deadline: May 31st
A novelty at ESSLLI'96 is the student session. The purpose of
the student session is to provide students with an opportunity
to present their work in progress and get valuable feedback by
senior researchers and "colleague-students".
To that end, students are encouraged to submit papers describing
*work in progress* (so as to benefit most from feedback). The emphasis
will be on papers that show creativity, innovative ideas and promise
rather than on papers that present well-polished results.
The student session has been designated its own timeslot in the
schedule of ESSLLI'96. Such basically means that there will be
a 90-minutes student session EVERY DAY. Depending on the number
and quality of submitted papers, either only in the first
week or in both weeks. The session will not be a poster session!
Students will be presenting their work in a 20+10 minutes talk.
The areas of interest are essentially the areas of the summer
school: Logic, Language, Computation, Logic & Language, Logic &
Computation, and Language & Computation. A comprehensive but surely
not complete list of topics:
LOGIC
intuitionistic logic, many-valued logic,
fuzzy logic, quantification logic, logic and uncertainty,
logic of action, BDI logics, process logics, abduction, non-monotonic
reasoning, modal logic, temporal logic, mathematical foundations of
computer science, dynamic logic, model theory ......
LANGUAGE
syntax, semantics, pragmatics, phonology, morphology, phonetics,
topic-focus structure, discourse, contextual reference,
quantification, presupposition, thematic relations, rhetorical
relations ....
COMPUTATION
concurrent systems, intelligent agents, multi-agent worlds, genetic
algorithms, computer-aided education, neural networks, planning,
probabilistic reasoning, qualitative reasoning, theorem proving,
constraint-based reasoning ....
LOGIC & COMPUTATION
abductive/deductive/inductive logic programming, finite model theory,
belief revision, cognitive modeling, common sense reasoning,
computational complexity, constraint satisfaction, knowledge acquisition,
knowledge representation ......
LOGIC & LANGUAGE
update semantics, dependency, dynamic semantics, formal semantics,
event-based semantics, intensionality, property theory, self-reference ....
LANGUAGE & COMPUTATION
connectionism, PDP-NLP, lexica, corpora, information retrieval,
statistical & probabilistical approaches to NLP, speech recognition,
speech generation, dialogue systems, comutational grammar formalisms,
parsing, machine learning of natural language, natural language
interfaces, integrating language and vision, machine translation .....
Submissions should not be longer than 5 pages, including references and
abstract but excluding a title page with the addresses of the authors
so as to facilitate anonymous reviewing. The 'stylesheet' for submissions
is: Font Times Roman 12pt, margins 1 inch all around, 1.5 line-spacing,
no columns.
Electronic submissions are highly encouraged, and should have arrived
with the program chair at Friday May 31st at 12am CET. Please, do send
the title page separately from your paper! Formats in which papers can
be submitted are Latex, RTF, and PostScript.
Address: Anne-Marie Mineur
Computerlinguistik, Bau 17.1
Postfach 151150
66041 Saarbruecken
Germany
E-mail: mineur@coli.uni-sb.de
Papers will be reviewed by a committee of students and co-chairs with
expertize in the respective areas. The (co-)chairs of the ESSLLI'96
Student Session are:
Program Chair: Anne-Marie Mineur
Logic: <to be filled in>
Language: Klaus Netter (Saarbruecken)
Computation: Peter van Roy (Saarbruecken)
Logic & Computation: Maarten de Rijke (Warwick)
Logic & Language: Paul King (Tuebingen)
Language & Computation: James Pustejovsky (Brandeis)
Local Chair: Geert-Jan Kruijff (Prague)
Note that, in order to present a paper at the ESSLLI'96 Student Session,
you have to register as a participant to ESSLLI'96. As a special benefit for
authors of accepted papers, registration at early registration fee will
be offered.
-------------------------- Anne-Marie Mineur ----------------------------
Computerlinguistik, Onderzoeksinstituut voor
Uni des Saarlandes Taal en Spraak (OTS/UU)
Postfach 151150, D-66041 Saarbruecken Trans 10, NL-3512 JK Utrecht
+ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
mineur@coli.uni-sb.de http://www.coli.uni-sb.de/~mineur mineur@let.ruu.nl
-----------------------------------------------------------------------
To: comp-ai-nlang-know-rep@uunet.uu.net
From: Carl_Edwards <s610755@tfh-berlin.de>
Subject: Query: German Grammar Checking Feasibility
Date: 19 Apr 1996 13:25:23 GMT
To: s610755@compute.tfh-berlin.de
I am currently working on a project to try and develop a system for checking
german texts for mistakes using a computer.
What I would like to know is:
Does anyone believe that it is possible to check the grammar in a piece of
german text without an understanding of what the sentence is supposed to
mean/say?
Personally, I don't believe this is possible, or rather that the quality of a
given check will increase in proportion to the amount of knowledge the computer
has over the world described in the text (which may not be necessarily a 'real'
world) and the computer's understanding of what the text is trying to say about
that world.
Currently I am playing with the idea of pairing nouns, verbs, etc... with the
sort of ideas they are used to express, for example:
eindringen => in + akk. = things the subject(s) can force its/their way into
subjekt = people, gas, water...
auf + jemandem
Obviously this is far too much information to store, represent and, just as
importantly, access quickly (the system should be interactive) given that I do
not wish to simply work on a tiny specialist subset of the german language.
However at this stage I am keeping things at a fairly high-level, with no fixed
model for representing the information I require.
I look forward to hearing any ideas anyone has about this. I will (eventually)
re-post this in German (I'm english and so any mistakes I make could be
embarrasing given the topic!) and will welcome any replies written in german. I
have little formal knowledge of natural language processing and would
appreciate any explanations of any jargon used.
Thanks.
/-\/-\ Carl Anthony Edwards
\o/\o/ e-mail: s610755@tfh-berlin.de
( )
--
-----------------------------------------------------------------------
Date: Fri, 19 Apr 96 10:46 BST
From: johnca@cogs.susx.ac.uk (John Carroll)
To: acl@cs.columbia.edu, acl@research.att.com, aisb@cogs.sussex.ac.uk,
Subject: CFP: ESSLLI'96 Robust Parsing Wkshp, Aug 96, Prague
WORKSHOP ON ROBUST PARSING - CALL FOR PAPERS
August 12 - 16, 1996
at ESSLLI'96
European Summer School in Logic, Language and Information
Prague, Czech Republic
BACKGROUND:
Parsing systems able to analyse natural language text robustly and
accurately at an appropriate level of detail would be of great value in
computer applications ranging from speech synthesis and document style
checking to message understanding and automatic translation. A number of
research groups worldwide are currently developing such systems, varying
in the depth of analysis from lexical parsing or tagging (identifying
syntactic features just of individual words), through shallow or phrasal
parsing (forming hierarchical syntactic structure but not exploiting
subcategorisation), to full parsers (which deal with unbounded
dependencies etc., and are able to recover predicate-argument structure).
To bring researchers in this area together to present and compare
state-of-the-art systems for robust parsing, a workshop will be held
August 12-16, 1996, during the first week of ESSLLI'96, the European
Summer School in Logic, Language and Information.
We invite the submission of papers describing implemented robust parsing
systems; also evaluations, comparisons, and critiques of different parsing
systems or technologies. The main aim of the workshop is to identify the
strengths and weaknesses in the diverse set of approaches currently being
investigated, and to discuss areas that require further work.
To facilitate comparison between systems, authors of accepted papers will
be supplied with a small corpus of 30 sentences and encouraged to run
these through their systems, using simple (supplied) criteria to evaluate
the results.
WORKSHOP STRUCTURE:
The workshop will consist of 5 90-minute sessions, with two papers in each
session. Please note that speakers will be expected to register for ESSLLI
(thus being eligible to attend all other workshops, as well as the many
courses and symposia). There is a small amount of money available to go
towards the expenses of those who have no other source of funding.
ORGANISERS:
John Carroll, University of Sussex
and Ted Briscoe, University of Cambridge
SUBMISSION DETAILS:
Authors should submit an extended abstract (2000-3000 words) either
electronically or as hard-copy. Electronic submissions must be either
plain ascii text or a single latex file. Your e-mail address should appear
on your paper, and unless requested otherwise, all further correspondence
will be conducted via e-mail.
SCHEDULE:
Submission Deadline: May 31
Notification of Acceptance: June 21
Final Papers for Inclusion in Proceedings: July 19
Workshop Dates: August 12-16, 1996
WORKSHOP SUBMISSIONS TO:
John Carroll
Cognitive and Computing Sciences,
University of Sussex,
Falmer, Brighton BN1 9QH, UK
E-mail: john.carroll@cogs.susx.ac.uk
SUMMER SCHOOL CONTACT:
ESSLLI'96,
UFAL MFF UK,
Malostranske' na'm. 25,
118 00 Praha 1,
Czech Republic
Fax: +42-2-2191-4-309
Phone: +42-2-2191-4-255
E-mail: esslli@ufal.mff.cuni.cz
WWW: http://ufal.ms.mff.cuni.cz
-----------------------------------------------------------------------
Date: Tue, 23 Apr 1996 10:38:06 +1000
From: morri@karl.cs.su.oz.au (Maurice Pagnucco)
Subject: Announcement: PRICAI-96 Pac. Rim AI Conf., Aug 96, Cairns
To: nl-kr@snyside.sunnyside.com
Reply-To: morri@cs.su.OZ.AU
FOURTH PACIFIC RIM INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE
CAIRNS, AUSTRALIA AUGUST 26-30, 1996
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
% PRICAI-96 will incorporate the annual Australian AI Conference, %
% AI'96 and is held in cooperation with the IEEE, the AAAI, the %
% JSAI, the ISAI and the ECAI. %
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
CALL FOR REGISTRATION
* * * * * * * * * * * * * *
* Full details concerning PRICAI-96 including full registration *
* information, accommodation, social programms and tours as well *
* as details of the Technical Program, Keynote Speakers, Panels, *
* Workshops and Tutorials can be found at: *
* *
* http://www.cit.gu.edu.au/research/groups/ai/pricai96/ *
* *
* * * * * * * * * * * * * *
The Pacific Rim International Conferences on Artificial Intelligence (PRICAI)
are biennial international events which concentrate on research and development
of AI technologies and their applications in areas of scientific, social,
and economic importance for countries in the Pacific Rim. PRICAI-96 will be
the fourth, and will be held August 26-30, 1996, at the Cairns Convention
Centre, in the Great Barrier Reef resort town of Cairns, on the east coast of
Queensland, Australia.
PRICAI-96 offers a high quality technical program on applications
and utilisation of AI and its techniques in emerging and dynamic
areas of the information technology and telecommunications industry such as
AI and networks, intelligent multimedia, virtual reality, networked
entertainment and games, financial modelling, learning and data mining,
enterprise modelling, and multi-lingual text and language processing.
PRICAI-96 will include:
* Technical Program:
This will be held on August 28 to 30. PRICAI-96 received 174 papers
and the PRICAI-96 Program Committee accepted 56 for presentation and
10 for poster presentation. The conference proceedings will be
published by Springer-Verlag.
* Keynote Speakers:
- Professor Marvin Minsky, MIT, USA
- Dr Juzar Motiwalla, ISS (NUS), Singapore
- Professor Joerg Siekmann, DFKI, Germany
* Panels:
- Robotics: Current Trends and Future Goals
Chair: Jane Hsu, National Taiwan University;
Rodney Brooks, MIT; Shin'ichi Yuta, Tsukuba University;
and Ray Jarvis, Monash University.
- Telecommunications and AI: Challenge and Opportunities
Chair: Rye Senjen, Telstra Research Labs
* Workshops:
PRICAI-96 will provide eight full-day workshops on August 26 and 27,
1996. Workshop participants will have the opportunity to meet and
discuss issues with a selected focus, providing an informal setting
for active exchange among researchers, developers and users on
topics of interest.
W1: THEORITICAL AND PRACTICAL FOUNDATIONS OF INTELLIGNET AGENTS
Contact: Lawrence Cavedon (cavedon@cs.rmit.edu.au)
W2: AI & TELECOMMUNICATIONS: THEORY AND PRACTICE
Contact: Rye Senjen (RSenjen@VTRLMEL1.TRL.OZ.AU)
W3: VALIDATION, VERIFICATION AND REFINEMENT OF KNOWLEDGE-BASED
SYSTEMS
Contact: Grigoris Antoniou (ga@cit.gu.edu.au)
W4: INDUCING COMPLEX REPRESENTATIONS
Contact: Srinivas Padmanabhuni (srinivas@cs.ualberta.ca)
W5: DISTRIBUTED ARTIFICIAL INTELLIGENCE
Contact: Dickson Lukose (lukose@peirce.une.edu.au)
W6: KNOWLEDGE-BASED INSTRUCTIONAL SYSTEMS IN AN INDUSTRIAL
SETTINGS
Contact: Leila Alem (leila@syd.dit.csiro.au)
W7: REASONING WITH INCOMPLETE AND CHANGING INFORMATION
Contact: Grigoris Antoniou (ga@cit.gu.edu.au)
W8: FUTURE ISSUES FOR MULTI-LINGUAL TEXT PROCESSING
Contact: Dominique Estival
(Dominique_Estival@muwayf.unimelb.edu.au)
* Tutorials:
PRICAI-96 will provide six half-day tutorials on August 26 and
27, 1996.
T1: EMBODIED INTELLIGENCE
Professor Rodney Brooks, MIT
T2: INTRODUCTION TO CONCEPTUAL STRUCTURES
Professor John F. Sowa, SUNY Binghamton
T3: AGENT-ORIENTED PROGRAMMING
Dr. Anand S. Rao, AAII
T4: PRACTICAL NATURAL LANGUAGE PROCESSING
Dr. Robert Dale, Microsoft Institute
T5: MACHINE LEARNING
A/Prof Claude Sammut, UNSW
T6: PRAGMATICS OF DEFAULT REASONING AND THEORY CHANGE
Drs G. Antoniou (Griffith University),
A. Nayak and A. Ghose (Sydney University)
* Conference Registration:
Advance Registration Late Registration
(before 19/7/96) (after 19/7/96)
Conference:
- Full Rate Aus $ 365 Aus $ 445
- Student Rate Aus $ 175 Aus $ 250
Workshops:
- Full/Student Rate Aus $ 65 Aus $ 100
Tutorials:
- Full Rate Aus $ 200 Aus $ 445
- Student Rate Aus $ 100 Aus $ 150
Please contact the Conference Secretariat for the full Registration Brochure
for any other information at:
Ms Susan Dickey
PRICAI-96 Secretariat
Finn Aussi Conference Services
PO Box 1689
Cairns, QLD 4870 Australia
Phone: +61 70 411 844
Fax: +61 70 411 244
Email: finnaussi@internetnorth.com.au
$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$
$ PRICAI-96 is sponsored by the Artificial Intelligence $
$ and Expert Systems Committee of the Australian Computer $
$ Society, the Australian Artificial Intelligence Institute, $
$ the Australian Tourist Commission, Continuum Ltd, the CRC $
$ for Advanced Computational Systems, the Distributed Systems $
$ Technology CRC Pty Ltd, Griffith University, the Institute $
$ of Systems Science (NUS) and the Queensland Government $
$ Department of Tourism, Small Business and Industry. $
$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$
-----------------------------------------------------------------------
Date: Wed, 24 Apr 1996 13:48:55 +0200
To: (Potential Participants)
From: dekker@illc.uva.nl (Paul Dekker)
Subject: Announcement: ILLC Logic Course via the Internet, Amsterdam
Call for Participation
LOGIC COURSE ON THE INTERNET: DYNAMIC SEMANTICS
The Institute for Logic, Language and Computation (Amsterdam) and the Dutch
Graduate School in Logic hereby announce the first of a planned series of
courses on the internet.
This first course is one on dynamic semantics, a discipline in the
semantics of natural language in which interpretation is conceived of as a
process essentially tied to change of information. The course is given by
Paul Dekker and David Beaver (both ILLC, Amsterdam). Additional
coordination by Erik-Jan van der Linden (also ILLC).
The course is meant for PhD students and advanced undergraduates who are
familiar with basic notions of logic and model-theoretic semantics.
Distinctive feature of this course is that it is held on the world wide
web. All communication (including an electronic classroom, readers,
collaboration on exercises etc.) takes place at the internet.
The course is given from May 3 to July 12. The course offers room for a
limited number (20) of participants, but it can also be followed by
observers who are professionally interested in the experiment. People who
are interested are adviced to subscribe soon. By following the course the
students can earn official credits (10 ECTS credits).
For more information on the course and on how to subscribe (both as a
participant and as an observer), the interested reader is referred to the
URL:
http://www.fwi.uva.nl/~pdekker/ECDS/
Paul Dekker, David Beaver, Erik-Jan van der Linden
Institute for Logic, Language and Computation
University of Amsterdam
-----------------------------------------------------------------------
From: Costas Spyropoulos <costass@iit.nrcps.ariadne-t.gr>
Subject: Announcement: MULSAIC'96 Multiling. S/W Wkshp, Aug 96, Budapest
To: nl-kr@snyside.sunnyside.com
Date: Wed, 24 Apr 1996 18:32:34 +0300 (EET DST)
Final Call for Participation
Multilinguality in the Software Industry:
The AI Contribution
(MULSAIC'96)
August 12, 1996, Budapest, Hungary
In conjunction with the ECAI'96 conference
(August 12 - 16, 1996)
WWW: http://www.iit.nrcps.ariadne-t.gr/~costass/mulsaic.html
Workshop Objectives
The objective of the workshop is to bring together people from the software
industry and the AI research community. In this way, it will provide an
opportunity for people from the software industry to present particular
problems and questions associated with multilinguality as well as an
opportunity for AI researchers to show that AI-based methods and tools can
help to find solutions and answers.
Workshop Background
The ability to develop products which can be adapted to the language and
culture of local markets is a prerequisite for software companies wishing
to be active internationally. This process, often known as Localisation,
has become an important and increasingly sophisticated part of the overall
development process. AI-based methods and tools can be used in the software
industry to build such multilingual software. AI contribution concerns not
only the use of AI in the software engineering process but also the
embedding of AI modules in the end products.
AI-based methods and tools have the potential to enhance the intrinsic
capability of products in a number of different application areas. For
example, they can be used to improve processes such as multilingual
information retrieval, multilingual generation of messages and
documentation, software translation.
Information retrieval and browsing systems of the future will need to be
knowledge-based. They will use knowledge representation techniques to
organise information in language-independent knowledge bases, make useful
associations and identify important information. Message generation systems
will use knowledge representation techniques to organise the software
knowledge in language-independent knowledge bases as well as natural
language generation techniques to generate messages on-line in the end-user
language. Automatic generation of documentation in more than one languages
will also be possible using knowledge representation and natural language
generation techniques. Knowledge representation techniques will be used for
the development of intelligent translation tools such as multilingual
terminological knowledge bases and translation memories, in order to
facilitate translation of software and documentation. Multilingual language
resources, such as lexica, grammars and morphological modules will be added
to software applications in order to improve functions such as spelling and
syntax checking in more than one languages.
Workshop Organisation
This workshop is structured around the following sessions:
- Software companies experiences concerning multilinguality.
Two large software companies will present their experiences in the subject.
- Multilingual information services.
Cross-lingual information retrieval on the WWW, distributed multilingual
information retrieval, multilingual network-based information services
are among the topics that will be discussed in this session.
- Multilingual resources and intelligent translation tools.
Automatic extraction of bilingual lexical equivalences from parallel
corpora, extraction of example phrases for bilingual dictionaries,
Example Based Machine Translation of Software Documentation, lingustic
considerations for multilingual software manuals are among the topics
that will be discussed in this session.
- Multilingual generation of messages and documentation.
Messages and documentation generation systems that use knowledge
representation and natural language generation techniques to generate
multilingual mesages and documentation respectively will be discussed here.
- Summarisation and a general discussion.
Organising Committee
- Costas Spyropoulos, N.C.S.R. "Demokritos", Athens, Greece
(costass@iit.nrcps.ariadne-t.gr)
- Joerg Schuetz, IAI, Saarbrucken, Germany (joerg@iai.uni-sb.de)
- Aarno Lehtola, VTT, Helsinki, Finland (aarno.lehtola@vtt.fi)
- Richard Sutcliffe, University of Limerick, Limerick, Ireland
(richard.sutcliffe@ul.ie)
- Alan Barrett, Lotus Development, Dublin, Ireland (abarrett@crd.lotus.com)
Workshop Format and Attendance Requirements
The format of the workshop will encourage interaction and discussion
between people from software industry and AI researchers. Invited speakers
from the software industry will present particular problems and questions
concerning multilinguality. There will be two types of submission for
interested participants: papers and statements of interest.
There will be a limited number of participants, around 30 - 40 people.
Please note that ECAI charges a fee of ECU 50 for each participant
of each workshop in addition to the normal ECAI-96 registration fee.
The workshop participation is not possible without registration
(http://www.dfki.uni-sb.de/ecai96/Registration.html) for the
ECAI'96 conference.
Submission Guidelines
Interested authors are requested to submit a camera-ready copy of
their paper of up to 10 pages, according to the ECAI-96 instructions
(http://www.dfki.uni-sb.de/ecai96/Instructions.html) before the
15th of May 1996. The paper should start with the title, authors,
full address, telephone, fax, e-mail, and the abstract. The authors
are requested to state clearly the problem examined and the AI method
used as well as to discuss the costs and benefits of their approach.
Performance evaluation results are also encouraged.
Other potential participants are requested to send a one page summary
of their interests and experience on relevant matters before the
1st of June 1996.
Submissions should be done through e-mail and addressed to
costass@iit.nrcps.ariadne-t.gr
For any questions, please contact:
Costas Spyropoulos,
Institute of Informatics & Telecommunications,
National Centre for Scientific Research (N.C.S.R.) "Demokritos",
15310 Aghia Paraskevi, Athens, Greece
E-mail: costass@iit.nrcps.ariadne-t.gr
Tel: +301-6510310, +301-6513110 ext.520, Fax: +301-6532175
Deadlines
Submission of paper: May, 15, 1996
Notification of acceptance: June, 1, 1996
Statement of interest: June, 1, 1996
Workshop Notes
All participants will receive copies of the accepted papers. Note also
that if there is sufficient interest we intend to publish the workshop
results in a book.
++
| Dr. Constantine D. Spyropoulos |
| Research Director Tel.: +30-1-6513110-19 ext. 520 |
| Software and Knowledge Engineering Laboratory +30-1-6510310 (secretary) |
| Inst. of Informatics & Telecommunications Fax : +30-1-6532175 |
| N.C.S.R. "Demokritos" |
| 15310 Aghia Paraskevi |
| Greece e-mail: costass@iit.nrcps.ariadne-t.gr |
++
-----------------------------------------------------------------------
Date: Mon, 29 Apr 1996 12:25:24 -0500
From: rsun@cs.ua.edu (Ron Sun)
To: neuron-request@cattell.psych.upenn.edu, nl-kr@cs.rpi.edu
Subject: Announcement: Report on Hybrid Systems, R. Sun, Alabama
Hybrid Connectionist-Symbolic Models:
a report from the IJCAI'95 workshop on connectionist-symbolic integration
Ron Sun
Department of Computer Science
The University of Alabama
Tuscaloosa, AL 35487
---------------------------------------
To appear in: AI Magazine, 1996.
9 pages.
ftp or Mosaic access:
ftp://cs.ua.edu/pub/tech-reports/sun.ai-magazine.ps
sorry, no hardcopy available.
----------------------------------------
{\it The IJCAI Workshop on Connectionist-Symbolic Integration: From
Unified to Hybrid Approaches} was held for two days
during August 19-20 in Montreal, Canada, in conjunction with the
Fourteenth International Joint Conference on Artificial Intelligence(IJCAI'95).
The workshop was co-chaired by Ron Sun and Frederic Alexandre.
During the two days of the workshop, various presentations and discussions
brought to light many new ideas, controversies, and syntheses.
The focus was on learning and architectures that feature hybrid representations
and support hybrid learning.
Hybrid models involve a variety of different types of processes and
representations, in both learning and performance.
Therefore, multiple mechanisms interact in complex ways in most models.
We need to consider seriously ways of structuring these different components,
which thus occupy a clearly more prominent place in this area of research.
The hybridization of connectionist and symbolic models also
inherits the difficulty with learning from the symbolic
side, and mitigates to some large extent the advantage that the purely
connectionist models have in their learning abilities.
Considering the importance of learning, in both modeling cognition and
building intelligent systems, it is crucial for researchers in this area
to pay more attention to ways of enhancing hybrid models
in this regard and to putting learning back into hybrid models.
End of NL-KR Digest
*******************
