LINGUIST List 8.1360

Thu Sep 25 1997

Calls: Machine Learning to Discourse

Editor for this issue: Anita Huang <anitalinguistlist.org>

Directory

1. Nancy Green, 2nd CFP: Applying Machine Learning to Discourse Processing

Applying Machine Learning to Discourse Processing 

 AAAI 1998 Spring Symposium Series
 Stanford University, California, March 23-25, 1998

Following success in using machine learning (ML) techniques in areas
such as speech recognition, part-of-speech tagging, word sense
disambiguation, and parsing, there has been an increasing interest in
applying ML to discourse processing. To date, there has been work in using
machine learning techniques such as inductive learning methods (decision 
trees), statistical learning methods (HMMs), neural networks, and genetic
algorithms to a number of discourse problems, e.g., dialogue act
prediction, cue word usage, anaphora resolution, initiative tracking,
and discourse segmentation.

In this symposium, we would like to bring together researchers with an
interest in exploring the potential contribution of ML to problems in
discourse interpretation and generation. Our goal is provide an
opportunity for discussions among researchers in natural language discourse
and in machine learning to facilitate collaboration between the two groups. We
are interested in addressing the following issues:

 * From the discourse processing point of view:
 - What tasks in discourse understanding/generation are most suitable
 for processing using ML-acquired models?
 - What are the features of these tasks that make them particularly 
 suitable for processing using ML-acquired models?
 - Which ML approaches successfully adopted by other areas of natural 
 language processing seem promising for use in discourse processing?
 And why?
 - Is it possible to base the entire discourse processing component of
 a natural language system purely on ML-acquired models?
 If not, when should models acquired by traditional approaches come 
 into play? And how should the two approaches be integrated?
 - How can learning be performed during the discourse comprehension or
 generation process?
 - How can knowledge acquired for discourse interpretation or
 generation be reused for the other?
 - What types of pragmatic knowledge (e.g., discourse recipes, cue
 phrase classification) can be acquired by ML?
 - What kinds of categories and features can be tagged automatically
 and/or reliably? How can useful features be identified?

 * From the machine learning point of view:
 - What are the different ML techniques that may be suitable for
 acquiring knowledge for discourse processing?
 - What are the features of these ML techniques that make them 
 particularly suitable for application in discourse processing?
 - How does the performance (e.g., accuracy, processing speed) 
 of models for discourse processing based on ML techniques compare 
 to those based on traditional methods?
 - How do different ML techniques compare with one another in terms of
 accuracy, efficiency, amount of data needed for training, etc, for
 various problems in discourse processing?
 - What discourse corpora are current available for ML? What other
 corpora are needed for ML research?
 - What characteristics of discourse processing cause problems for
 existing ML techniques?

The tentative symposium format includes short tutorials on ML
techniques, presentations of technical papers, as well as sessions for
experience-sharing and discussion of the above issues.

SUBMISSIONS:

Authors may submit one of the following:

- A technical paper (8 pages maximum) describing research in discourse 
 involving ML techniques. Please provide a brief abstract including 
 1) form of discourse addressed: text or dialogue, 2) type of
 processing addressed: generation, interpretation, or both, and 3) machine
 learning techniques employed.
- A position paper (3 pages maximum) addressing any of the issues listed
 in the CFP or other issues related to the symposium theme.
- A statement of interest describing your prior experience and
 publications related to the symposium theme. 

For each author provide name, affiliation, and (optional) home page URL.
If the paper has multiple authors, please designate one author to be the
primary contact and indicate which of the authors would like to be
invited to attend. For the primary contact and for each author who would like
to be invited to attend, please provide name, physical and electronic
mailing addresses, and daytime telephone and fax numbers.

Papers may be submitted either electronically (preferred) or in
hardcopy. Electronic submissions can be in plain ASCII text, or in pdf
or
postscript. Alternatively, papers can be prepared in HTML and a web
address
can be submitted. Submissions should be sent to:

 Jennifer Chu-Carroll
 Bell Laboratories, Rm 2C-440
 600 Mountain Avenue
 Murray Hill, NJ 07974, USA
 
 Phone: 908-582-5037
 E-mail: jenccbell-labs.com

Hardcopy submissions are due October 24, 1997. Electronic submissions
should be received no later than October 21 to ensure that we are able
to access them. Authors will be notified of acceptance/rejection decision
around November 14, 1997.

PROGRAM COMMITTEE:

 Jennifer Chu-Carroll (co-chair), Bell Laboratories
 jenccbell-labs.com 
 Nancy Green (co-chair), Carnegie Mellon University 
 Nancy.Greencs.cmu.edu
 Barbara Di Eugenio, University of Pittsburgh
 Peter Heeman, Oregon Graduate Institute
 Diane Litman, AT&T Labs - Research
 Raymond Mooney, University of Texas -- Austin
 Johanna Moore, University of Pittsburgh
 David Powers, Flinders University

For more information about this symposium, see our web site:
http://www.cs.cmu.edu/afs/cs.cmu.edu/user/ngreen/public-web-pages/sss-98.html