9.1195, Calls: GLAC-5, Neural Symbolic Processing

LINGUIST Network linguist at linguistlist.org
Fri Aug 28 17:57:47 UTC 1998

LINGUIST List:  Vol-9-1195. Fri Aug 28 1998. ISSN: 1068-4875.

Subject: 9.1195, Calls: GLAC-5, Neural Symbolic Processing

Moderators: Anthony Rodrigues Aristar: Wayne State U. <aristar at linguistlist.org>
            Helen Dry: Eastern Michigan U. <hdry at linguistlist.org>

Review Editor: Andrew Carnie: U. of Arizona <carnie at linguistlist.org>

Editors:  	    Brett Churchill <brett at linguistlist.org>
		    Martin Jacobsen <marty at linguistlist.org>
		    Elaine Halleck <elaine at linguistlist.org>
                    Anita Huang <anita at linguistlist.org>
                    Ljuba Veselinova <ljuba at linguistlist.org>
		    Julie Wilson <julie at linguistlist.org>

Software development: John H. Remmers <remmers at emunix.emich.edu>
                      Zhiping Zheng <zzheng at online.emich.edu>

Home Page:  http://linguistlist.org/

Editor for this issue: Martin Jacobsen <marty at linguistlist.org>

Please do not use abbreviations or acronyms for your conference unless
you explain them in your text.  Many people outside your area of
specialization will not recognize them. Also, if you are posting a
second call for the same event, please keep the message short.  Thank
you for your cooperation.


Date:  Thu, 27 Aug 1998 16:20:50 -0500
From:  "Mark L. Louden" <louden at mail.utexas.edu>
Subject:  Germanic Linguistics Annual Conference-5, 1999

Date:  Fri, 28 Aug 1998 19:14:05 +0100
From:  Stefan Wermter <stefan.wermter at sunderland.ac.uk>
Subject:  Call: Neural Symbolic Processing

-------------------------------- Message 1 -------------------------------

Date:  Thu, 27 Aug 1998 16:20:50 -0500
From:  "Mark L. Louden" <louden at mail.utexas.edu>
Subject:  Germanic Linguistics Annual Conference-5, 1999

Germanic Linguistics Annual Conference-5

will take place at the University of Texas at Austin, April 16-18,

We invite colleagues at all levels (faculty and graduate students) to
submit abstracts for 30-minute papers on any linguistic or
philological aspect of any historic or modern Germanic language or
dialect, including English (to 1500) and the extraterritorial
varieties.  Papers from a range of linguistic subfields, including
phonetics, phonology, morphology, syntax, semantics, sociolinguistics,
language acquisition, contact, and change, as well as differing
theoretical approaches, are especially welcome.

Please send to the address below a one-page, 12-point font abstract
that is headed only by the title of your paper, as well as a separate
3" x 5" index card with your name, institutional affiliation, mailing
address, phone/fax numbers, e-mail address, and the title of your
paper.  Submissions must be received by January 2, 1999.
Notifications of acceptance will be sent out by February 1, 1999.

Department of Germanic Studies
E. P. Schoch 3.102
University of Texas at Austin
Austin, Texas 78712

For more information, e-mail Prof. Mark L. Louden
(louden at mail.utexas.edu) or Prof. Mark R. V. Southern
(m.southern at mail.utexas.edu).  As of October 1, 1998, you may also
consult the GLAC-5 website via the UT Germanic Studies departmental
website at www.utexas.edu/depts/german/main.html.

-------------------------------- Message 2 -------------------------------

Date:  Fri, 28 Aug 1998 19:14:05 +0100
From:  Stefan Wermter <stefan.wermter at sunderland.ac.uk>
Subject:  Call: Neural Symbolic Processing

                 NIPS*98 Conference Workshop

(part of International Conference on Neural Information Processing
                      December 4 and 5, 1998
                      Breckenridge, Colorado

                    Hybrid Neural Symbolic Integration

                Stefan Wermter, University of Sunderland, UK
                    Ron Sun, University of Alabama, USA

Description and motivation
- -----------------------

In the past it was very controversial whether neural or symbolic
approaches alone will be sufficient to provide a general framework for
intelligent processing. In recent years, the field of hybrid neural
symbolic processing has seen a remarkable development. The motivation
for the integration of symbolic and neural models of cognition and
intelligent behavior comes from many different sources.

>>From the perspective of cognitive neuroscience, a symbolic
interpretation of an artificial neural network architecture is
desirable, since the brain has a neuronal structure and the capability
to perform symbolic processing. This leads to the question how
different processing mechanisms can bridge the large

gap between, for instance, acoustic or visual input signals and
symbolic reasoning for instance for language processing, inferencing,

>>From the perspective of knowledge-based processing, hybrid
neural/symbolic representations are advantageous, since different
mutually complementary properties can be integrated. Symbolic
representations have advantages with respect to easy interpretation,
explicit control, fast initial coding, dynamic variable binding and
knowledge abstraction. On the other hand, neural representations show
advantages for gradual analog plausibility, learning, robust
fault-tolerant processing, and generalization to similar input. Since
these advantages are mutually complementary, a hybrid symbolic
connectionist architecture can be useful if different processing
strategies have to be supported.

Areas of interest
- ---------------

- Integration of symbolic and neural techniques for

    - integrating techniques for language and speech processing
    - integrating different modes of reasoning and inferencing
    - combining different techniques in data mining
    - integration for vision, language, multimedia
    - hybrid techniques in knowledge based systems
    - combining fuzzy/neuro techniques
    - neural/symbolic techniques and applications in engineering

- Exploratory research in
    - emergent symbolic behavior based on neural networks
    - interpretation and explanation of neural networks
    - knowledge extraction from neural networks
    - various forms of interacting knowledge representations
    - dynamic systems and recurrent networks
    - evolutionary techniques for cognitive tasks (language,
      reasoning, etc)

- Autonomous learning systems for cognitive agents
    that utilize both neural and symbolic learning techniques

- ----

The workshop should provide a forum for presenting and discussing
theory and practice of neural/symbolic integration.  The format will
consist of position statements/panel, group discussion and individual
paper presentations.  We intend to reserve a significant portion of
time for open discussion.  The proposed length of the workshop is two

Suggested panels are:

1.Connectionist models for language, vision, inferencing.  What are
principles for neural/symbolic representation?

2. Hybrid neural models for new media (multimedia, web searching,
digital libraries, etc) What will be the impact of hybrid techniques
in the future?

- ---------------

It is intended to publish the results after the workshop, either in a
book (Springer) or via a special issue of a journal.  We invite papers
which can take two forms: short position papers (around 4 pages) or
full papers (up to 12 pages).

We intend to process submissions electronically.  Please a postscript
file via ftp (see below). The paper format should be compatible with
latex article format: 11pt, 12 pages maximum, including title, address
and email address, abstract, figures, references. Notifications will
be sent by email to the first author.

Postscript files can be uploaded with anonymous ftp.  Please send a
notification message to stefan.wermter at sunderland.ac.uk

ftp isis.sunderland.ac.uk (
login: anonymous
password: <your email address>
cd pub/wermter
put <yourfile.ps> or <yourfile.ps.gz>

The paper must arrive not later than 25th September  1998
at the address below.

##############Submission Deadline:  25th September 1998

For an update on invited speakers, panel and information please see

Please send correspondence to:
NIPS Workshop Contact
- -------------------

Professor Stefan Wermter
Research Chair in Intelligent Systems
University of Sunderland
School of Computing & Information Systems
St Peters Way
Sunderland SR6 0DD
United Kingdom

phone: +44 191 515 3279
fax:   +44 191 515 2781
email: stefan.wermter at sunderland.ac.uk

LINGUIST List: Vol-9-1195

More information about the Linguist mailing list