LINGUIST List 7.40

Tue Jan 9 1996

Calls: New Directions in Planning & Natural Language Generation

Editor for this issue: Anthony M. Aristar <>


  1. Kristiina Jokinen, CFP: Gaps and Bridges - New Directions in Planning and Natural Language Generat ion

Message 1: CFP: Gaps and Bridges - New Directions in Planning and Natural Language Generat ion

Date: Wed, 10 Jan 1996 12:52:06 +0900
From: Kristiina Jokinen <>
Subject: CFP: Gaps and Bridges - New Directions in Planning and Natural Language Generat ion


 ECAI-96 Workshop



 New Directions in Planning and Natural Language Generation


 12th European Conference on Artificial Intelligence

 August 12 or 13, 1996
 Budapest, Hungary

Recent research on autonomous cooperative systems has shown that linguistic
knowledge is not enough for successful communication: strategic planning, which
is prior to and independent of language, plays a key role in planning
communicative contributions. There has also been a focus shift in NLG from the
study of well-formedness conditions (grammars) to the exploration of
communicative adequacy of linguistic forms: speaking is viewed as an indirect
means for achieving communicative goals rather than an exercise to produce
grammatically correct output. Moreover, new ideas like rational agency (Cohen
and Levesque 1990), conflict resolution (Galliers 1989) and resource-bounded
agency (Bratman, Israel and Pollack 1988) have become central issues within thi
larger framework: they affect not only planning, but also the realisation of

Despite a growing awareness of the importance of these issues, there is still
relatively little work showing ways of integrating them into a system. Yet, one
of the most important areas in AI research is the establishment of a link
between NLG-systems and intelligent planning systems.

This workshop aims at clarifying the role of rational and cooperative planning
in generation, contributing to the ultimate goal of building a computational
model that integrates these components into a unified whole. Furthermore, the
workshop provides an opportunity to examine theoretical models of planning
agents and their impact on practical aspects of NLG architecture.

Contributions dealing with the following topics are particularly welcome:

- generation viewed as a rationally, cooperatively planned goal-
 oriented activity;

- interactions between situational, motivational (speaker and
 addressee goals), cognitive and linguistic constraints;

- generation of discourse based on techniques developed in AI and
 computational linguistics;

- the effect of the various constraints on the generation process
 as a whole (resource-bounded agency and planning constraints;
 open-world assumption; time and space constraints);

- planning strategies: reactive vs. deliberate planning, anytime
 planning, resource-bounded planning;

- quantitative methods based on corpus analysis (showing which
 linguistic or communicative acts are instrumental in a given
 setting), statistical and stochastic models; evaluation.


The workshop will be kept small, with a maximum of 40 participants. Preference
will be given to active participants selected on the basis of their submitted
papers. A small number of participants without a paper will also be considered;
such persons should submit a 1-2 page statement of interest and a list of
relevant publications. No-paper participants will be requested to give comments
on the accepted papers.

According to ECAI rules, all workshop attendees must register for the main
ECAI-96 conference. In addition, there is a separate workshop registration fee
of ECU 50.

More information about registration can be found at ECAI-96 Registration page


The workshop is intended to be a genuinely interactive event with constructive
development and exchange of ideas rather than a mini-conference. Participants
are asked to read some of the articles mentioned in the workshop description
before their arrival. Yet, rather than aiming at a consensus for a particular
theory or research direction, the participants are encouraged to present
thought-provoking ideas which allow for vivid and vigorous discussions.

Being aware of the lack of communication between theorists and engineers, the
workshop also aims at bridging this gap. Besides emphasizing the innovative
aspects of research and their potential for practically oriented work,
discussion of practical applications as testbeds for theory will be encouraged.
The workshop aims at building a common ground allowing a productive interaction
between these two groups.

The one-day workshop is structured around individual presentations, group
discussions and a panel discussion. The presentations should not exceed 20
minutes, in order to encourage the speakers to reach quickly the point they wan
to make. Every session is followed by an open, 30 minute group discussion. Thus
new and thought provoking ideas may serve as starting points for a discussion,
allowing each participant to contribute to its development from their own

Demonstration of software could be organised as part of the main ECAI


Potential participants are invited to submit extended abstracts on the topics
outlined above. Submissions should be no longer than 5 pages, single spaced,
and be in line with the ECAI-style sheet, obtainable from

Electronic submissions should be sent to:

Alternatively, three hardcopies of the extended abstract can be mailed to
Kristiina Jokinen at the address below.

Accepted submissions will be published in the proceedings of the workshop
which will be distributed to each participant.



 How important is the work reported? Does it attack an important and/or
 difficult problem? Does the approach have the potential for improving
 the state of the art? Does the work stimulate discussion on important
 issues, or an alternative point of view?


 Has this or similar work been previously reported? Are the problems and
 approaches completely new? Is this a novel combination of familiar
 techniques? Does the paper point out differences with related research ?
 Does it introduce an idea that appears promising or might stimulate
 others to develop promising alternatives?


 Is the paper technically sound? Does it carefully evaluate the strengths
 and limitations of its contributions? How are its claims backed up?


 Is the paper clearly written? Does it motivate the research? Does it
 specify the inputs, outputs and basic algorithms employed? Is the
 paper written in a manner that makes its content accessible to most
 AI researchers?


 Is the paper germane to the focused topic of the workshop? Would it be
 better served to be published/presented elsewhere?


March 15 Deadline for submission of extended abstracts (5 pages)

April 15 Notification of acceptance

May 20 Final paper for the working notes


Kristiina Jokinen
Computational Linguistics Laboratory
Graduate School of Information Science
Nara Institute of Science and Technology
8916-5 Takayama, Ikoma, Nara
630-01 JAPAN
Tel: 81-7437-2-5242
Fax: 81-7437-2-5249

Mark Maybury
Artificial Intelligence Center
MITRE Corporation, MS K308
202 Burlington Road
Bedford, MA 01730-1420
Tel: (617) 271-7230
Fax: (617) 271-2352

Michael Zock
B.P. 133, 91403 Orsay, FRANCE
Tel: 331- 69 85 80 05
Fax: 331- 69 85 80 88


Should you have any questions or need additional information on the workshop,
please contact Kristiina Jokinen by e-mail ( or at the
address above. The call for papers can be obtained from Gaps and Bridges home
page at

Further information on the ECAI-96 conference, including updated information
on hotel and travel information, can be obtained fom the ECAI home page at

Information on the ECAI Workshops is listed at ECAI workshop page

Updated information on this workshop and the final papers will be made availabl
via the Gaps and Bridges home page, reachable also via the ECAI workshop page.

Mail to author|Respond to list|Read more issues|LINGUIST home page|Top of issue