5.0765 CFP: Probabilistic Approaches to Natural Language (1/118)
Elaine Brennan & Allen Renear (EDITORS@BROWNVM.BITNET)
Mon, 16 Mar 1992 10:14:26 EST
Humanist Discussion Group, Vol. 5, No. 0765. Monday, 16 Mar 1992.
Date: Fri, 13 Mar 1992 14:14 EST
From: "NANCY M. IDE (914) 437 5988" <IDE@VASSAR>
Subject: AAAI Symposium
From: Robert Goldman <email@example.com>
Call for Participation
AAAI Fall Symposium on
PROBABILISTIC APPROACHES TO NATURAL LANGUAGE
AAAI Fall Symposium Series
October 23, 24, & 25, 1992
Royal Sonesta Hotel
Sponsored by the
American Association for Artificial Intelligence
445 Burgess Drive, Menlo Park, CA 94025
The American Association for Artificial Intelligence presents the 1992 Fall
Symposium Series, to be held Friday through Sunday, October 23--25, 1992,
at the Royal Sonesta, Cambridge, Massachusetts.
The topics of the five symposia in the 1992 Fall Symposium Series are:
Applications of AI to Real-World Autonomous Mobile Robots;
Design from Physical Principles;
Intelligent Scientific Computation;
Issues in Description Logics: Users Meet Developers;
Probablistic Approaches to Natural Language.
Most symposia will be limited to approximately 60 participants. Each
participant will be expected to attend a single symposium. Working notes
will be prepared and distributed to participants in each symposium.
A general plenary session will be scheduled in which the highlights of each
symposium will be presented and an informal reception will be held on
Friday evening, October 23.
In addition to invited participants, a limited number of other interested
parties will be allowed to register in each symposium. Registration
information will be available in July 1992. To obtain registration
information write to the address above.
Submission requirements vary with each symposium, and are listed in the
descriptions of the symposia. Please send your submissions directly to the
address given in the description. DO NOT SEND submissions to AAAI. All
submissions must arrive by May 11, 1992. Acceptances will be mailed by June
8, 1992. Material for inclusion in the working notes of the symposia will
be required by August 10, 1992.
Probabilistic Approaches to Natural Language
Recently there has been a resurgence of interest in probabilistic methods
in AI, spurred by technical developments which have made these methods more
practical. Bayesian and decision-theoretic approaches have been
facilitated by the development of graphical representations such as belief
(or Bayesian) networks, and influence diagrams. Learning approaches have
been promoted by new developments in statistical learning (particularly
Hidden Markov Models). These methods all offer hopes to address problems
of brittleness and knowledge representation in Natural Language Processing.
Each has its own special strengths, however. Bayesian approaches have a
clear conceptual framework and powerful representations, but must still be
knowledge-engineered, rather than trained. Hidden Markov Models have a
clear conceptual framework and the ability to learn, but structure must be
given, and the model is weak.
This symposium which will bring together researchers applying both of these
probabilistic methods in order to share perspectives. We intend that the
discussion will emphasize reviews of the current state of the art and views
of the most promising lines of research.
Of particular interest are novel applications of statistical and Bayesian
techniques, systems which add more complicated knowledge representations to
statistical methods or adaptive Bayesian methods. We are also interested
in research where Bayesian and statistical methods are use to solve
foundational issues in knowledge representation, natural language semantics
and acquisition of semantic representations.
Some examples of such research are:
1. The use of statistical methods to extract information from text.
2. Combining primary source evidence from large corpora with dictionary
knowledge for various applications, including part of speech tagging, sense
discrimination/disambiguation, and bilingual word/phrase matching.
3. Using Bayesian methods to implement abductive approaches to NL
4. Probabilistic approaches to Machine Translation.
5. Combining high-level knowledge with low-level speech recognition.
6. Indexing and retrieval of concepts from text.
Those wishing to attend the symposium should submit a 1-page statement of
research interests and accomplishments, and a bibliography of selected
publications. Those wishing to present their work for discussion should
submit, in addition, an extended abstract of no more than 4 pages.
Potential participants should submit these materials by electronic mail to
firstname.lastname@example.org. If this is for some reason impossible, four copies of a
printed document may be submitted to
Computer Science Department
301 Stanley Thomas Hall
New Orleans, LA 70118-5698 U.S.A.
All submissions must be received by May 11, 1992.
Program Committee: Robert Goldman, Peter Norvig, Eugene Charniak, Bill