Applying Machine Learning to Discourse Processing
AAAI 1998 Spring Symposium Series
Stanford University
March 23-25
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 currently 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.
October 21, 1997 -- Electronic submissions are due
October 24, 1997 -- Hardcopy submissions are due
November 14, 1997 -- Acceptance/rejection notices are mailed out
January 17, 1998 -- Camera-ready papers due
February 6, 1998 -- Invited participants registration deadline
February 27, 1998 -- Final (open) registration deadline
March 23-25, 1998 -- Spring Symposium Series, Stanford University
Symposium Information
Call for Participation (ascii)
Submission Information
Accepted Papers
Symposium Schedule (HTML with links to papers)
Symposium Schedule (postscript)
Working Notes Table of Contents
Information for authors of accepted papers
AAAI
AAAI
1998 Spring Symposium Series
Program Committee
Jennifer Chu-Carroll (co-chair)
Bell Laboratories (jencc@bell-labs.com )
Nancy
Green (co-chair), Carnegie Mellon University (Nancy.Green@cs.cmu.edu)
Barbara Di Eugenio , University
of Pittsburgh
Peter Heeman, Oregon
Graduate Institute
Diane Litman, AT&T
Laboratories Research
Raymond Mooney , University
of Texas
Johanna Moore, University
of Pittsburgh
David
Powers , Flinders University
Related Links
ACL SIGNLL
Discourse
Resource Initiative
UCI: Information
Related to Machine Learning