HLT-NAACL / NSF WORKSHOP
Research Directions in Dialogue Processing
May 31st - June 1st, 2003
Edmonton, Alberta, CANADA
Researchers and product engineers have begun to develop increasingly
sophisticated dialogue capabilities for spoken language systems. Their
experience is rapidly creating information and artifacts which in turn
are attracting increasing interest on the part of researchers from a
variety of disciplines. One reason for this ferment is that groups who
traditionally have had little opportunity to interact with each other,
linguists, computational linguists, speech scientists and engineers,
each approaching dialog from different perspectives, have begun to
interact on a technical level. In part this is due to the emergence of
working technologies, such as recognition systems and speech
synthesizers, that for the first time allow researchers not directly
familiar with the implementation of component technologies to put
together systems that converse (however simply) with humans. As a
result, groups with very different traditions now find themselves
working on phenomena that are nominally the same. These researchers
are concerned about making use of linguistically motivated dialogue
models, the need for well-engineered, practical interfaces for use
with everyday users, and the availability of corpora that can steer
new research in this area for both computational linguists and
engineers.
These shared concerns present an opportunity to encourage
cross-fertilization and to transform the study of dialog into a richer
and more energetic enterprise. In turn, such a transformation will
increase our scientific understanding of dialog and will hasten the
creation of techniques and artifacts that significantly impact
human-computer communication.
The purpose of this workshop is identify common research concerns and
to identify paradigms, tools, corpora, evaluation techniques and other
infrastructure that will promote the scientific study of dialogue.
Submission of Position Papers
Contributions are invited from active practitioners in the field of
dialog processing and can address one of the following topics:
* acquisition and decoding of signals
* multi-modal integration
* language understanding
* dialog management
* pragmatics
* output planning
* language generation
* rendering through speech and other modes
Each position paper may address one or more of the following issues:
* identify successful research paradigms
* identify accepted or emerging evaluation techniques
* identify corpora, both available and desired, that will drive research
In addition, all papers should discuss methods of sharing resources
(such as tools and corpora) across communities, for example though the
adoption or development of standards and through design for
reusability.
Submissions
Position papers should be no longer than 3 pages and should follow the
HLT/NAACL style (see
http://www.sims.berkeley.edu/research/conferences/hlt-naacl03/format.html).
Note that authors should identify themselves (in contrast to the
instructions for HLT/NAACL papers). To encourage a more productive
workshop, the organizers may ask groups of several authors to combine
their thoughts into a single presentation.
Position papers should be submitted in electronic form (either pdf or
postscript) to: dialogue2003@cs.cmu.edu
Deadline for submission: March 21st, 2003
Proceedings
Attendees will be invited to submit versions of their papers for
inclusion in workshop proceedings and to contribute to a summary
report.
Organizing Committee
Alexander I. Rudnicky, Carnegie Mellon University, air@cs.cmu.edu
Candace L. Sidner, Mitsubishi Electric Research Laboratories, sidner@merl.com
Website
http://www.speech.cs.cmu.edu/hltnaacl2003/
This archive was generated by hypermail 2b29 : Fri Mar 14 2003 - 09:22:30 MET