4.0591 Conf: Machine Learning of Language and Ontology (1/78)
Elaine Brennan & Allen Renear (EDITORS@BROWNVM.BITNET)
Mon, 15 Oct 90 20:36:30 EDT
Humanist Discussion Group, Vol. 4, No. 0591. Monday, 15 Oct 1990.
Date: Fri, 12 Oct 90 12:48:42 MET
From: David Powers AG Siekmann
Subject: AAAI Spring Symposium on Machine Learning of Natural Language
Machine Learning of Natural Language and Ontology
March 26-28 1991 - AAAI Spring Symposium - Stanford
Over the last thirty years there has been a trickle of papers addressing
aspects of the Natural Language Learning area. The 80s have even seen a
few books published on the subject. These have tended to take
drastically different theoretical approaches, and have drawn on varying
degrees on fields outside Computer Science and Artificial Intelligence.
During this same period, computational and mathematical modelling of
language and learning have increasingly been recognized as relevant to
assessing the validity of a theory of Language Acquisition or the Nature
of Language. Conversely, researchers in Linguistics, Psycholinguistics
and Philosophy, as well as Computing, have been considering how and
where we can apply our increasing knowledge of the human characteristics
and constraints which determine how we solve problems, learn about the
world, and use language.
The symposium will address all aspects of the relationship between
Machine Learning and Natural Language. We not only expect input from
researchers in Computer Science and Artificial Intelligence (Machine
Learning, Natural Language, Robotics, Vision, Neural Nets, Parallelism,
etc.) but wish particularly to encourage relevant contributions from
other fields (Linguistics, Psycholinguistics, Philosophy, Neurology,
Mathematics, etc.)
Specific areas of interest include:
Traditional Approaches
- Applicability of traditional machine learning.
- Applicability of traditional parsing techniques.
Complexity Theory
- Formal results on learning and language constraints.
- Development of effective classifications of language.
Cognitive Science
- Psychological results on language and restrictions.
- Linguistic results on the nature of natural language.
Parallel Networks
- Neural models of parsing and learning.
- Parallel models of parsing and learning.
Symbol Grounding
- Grounding of Natural Language Systems.
- Interaction between Modalities and Learning of Ontology.
System Development
- Computable hypotheses and heuristics for language learning.
- Experimental language learning systems and their rationale.
Prospective participants are encouraged to contact a member of the
symposium committee to obtain a more detailed description of the symposium
goals and issues. Participants should then submit an extended
abstract of a paper (500-1000 words) and/or a personal bio-history of
work in the area (300-500 words) with a list of (up to 12) relevant
publications.
We will acknowledge your e-mail enquiries or submissions promptly, and
will deal with other forms of communication as quickly as possible.
Submissions should be sent by e-mail to powers=sub@informatik.uni-kl.de
(and/or reeker@cs.ida.org) by November 16th. If e-mail is impossible, two
copies should be sent to arrive by November 16th to:
Larry Reeker, Institute for Defense Analyses, C & SE Div.,
1801 N. Beauregard St, Alexandria, VA 22311-1772
OR, fax a copy (with cover page) by November 16th BOTH to 1-703-820-9680
(Larry Reeker, USA) AND to +49-631-205-3210 (David Powers, FRG).
Program Committee: David Powers (chair - powers@informatik.uni-kl.de),
Larry Reeker (reeker@cs.ida.org), Manny Rayner (manny@sics.se),
Chris Turk (UK - Fax: +44-633-400091).