Applying Machine Learning to Discourse Processing

  • About Us
  • Gifts
  • AITopics
  • AI Magazine
  • Conferences
  • Library
  • Membership
  • Publications
  • Symposia
  • Contact

Applying Machine Learning to Discourse Processing

Papers from the AAAI Spring Symposium

Jennifer Chu-Carroll and Nancy Green,Cochairs

Technical Report SS-98-01
128 pp., $30.00
ISBN 978-1-57735-046-0
[Add to Cart] [View Cart]

Following success in using machine learning (ML) techniques in speech, syntactic, and semantic processing, there has been an increasing interest in applying ML to discourse problems such as dialogue act prediction, cue word usage, and discourse segmentation. This symposium will bring together researchers interested in exploring the potential contribution of ML to discourse interpretation and generation to address the following issues:

From the discourse processing point of view, issues include: What tasks in discourse understanding / generation are most suitable for processing using ML-acquired models? And why? Which ML approaches successfully adopted by other areas of natural language processing seem promising for use in discourse processing? And why? 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, issues include: 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?

AAAI Press

Ordering Information

Conference Reports

EAAI Symposium Reports

Fall Symposium Reports

Spring Symposium Reports

Workshop Reports

Press Books

Press Proceedings

Journals

For Authors

Permissions Requests

Other Links

AAAI Home Page

Awards

Calendar

Jobs

Meetings

AAAI Press

Resources

AAAI Workshops

Follow @RealAAAI

This site is protected by copyright and trademark laws under US and International law. All rights reserved. Copyright © 1995–2020 Association for the Advancement of Artificial Intelligence.
Your use of this site is subject to our Terms and Conditions and Privacy Policy | Home | About AAAI | Search | Contact AAAI
AAAI Conferences | AI Magazine | AITopics | Awards | Calendar | Digital Library | Jobs | Meetings | Membership | Press | Press Room | Publications | Resources | Symposia | Workshops