NINETEENTH INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE
August 1, 2005
4th Workshop on
Description of the Workshop
The workshop on Knowledge and Reasoning in Practical Dialogue Systems will focus on adaptivity in dialogue systems. We encourage both papers presenting successful adaptive dialogue systems as well as papers on potential drawbacks (or challenges).
This is the fourth workshop on Knowledge and Reasoning in Practical Dialogue System. The first workshop was organised at IJCAI-99 in Stockholm, the second workshop took place at IJCAI-2001 in Seattle, and the third workshop was held at IJCAI-2003 in Acapulco.
The current workshop includes research in three main areas: dialogue management, adaptive discourse planning, and automatic learning of dialogue policies. Probabilistic and machine learning techniques have significant representation, and the main applications are in robotics and information-providing systems.
The workshop notes contain 12 papers that address these issues from various view-points. The papers provide stimulating ideas and we believe that they function as a fruitful basis for discussions and further research.
Who should attend
This workshop aims at bringing together researchers and practitioners that work on the development of communication models that support robust and efficient interaction in natural language, both for commercial dialogue systems and in basic research.
It should be of interest also for anyone studying dialogue and multimodal interfaces and how to coordinate different information sources. This involves theoretical as well as practical research, e.g. empirical evaluations of usability, formalization of dialogue phenomena and development of intelligent interfaces for various applications, not excluding such areas as Robotics.
The workshop will encourage the participation of both system builders and theoretically oriented researchers, thus creating a forum for discussion across vocational and disciplinary borders. While taking practical applications and implemented dialogue systems as our point of departure, we emphasize the potential contributions of theoretical and empirical research: applications are the best testbeds for evaluating the usefulness and originality of theories and ideas.
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.
Each paper will be given ample time for discussion, more than what is customary at a conference. As said above, we encourage contributions of a critical or comparative nature that provide fuel for discussion. We also invite people to share their experiences of implementing and coordinating knowledge modules in their dialogue systems, and integrating dialogue components to other applications.
Program -- August 1, 20058:45 Welcome
Session 1 9:00 - 10:30 -- Approaches to dialogue management: talking to robots
K. Eliasson -- Towards a Robotic Dialogue System with Learning and Planning Capabilities
M. Niemann, S. George and I. Zukerman -- Towards a Probabilistic, Multi-layered Spoken Language Interpretation System
J. Wyatt -- Planning to resolve ambiguous references to objects
Session 2 11:00-12:10 -- Adaptive planning of output: experimental evaluation
M.E. Foster and M. White -- Assessing the Impact of Adaptive Generation in the COMIC Multimodal Dialogue System
P. Wärnestål -- Dialogue Strategy Evaluation of a Conversational Recommender System
K. Komatani, R. Hamabe, T. Ogata and H.G. Okuno -- Generating Confirmation to Distinguish Phonologically Confusing Word Pairs in Spoken Dialogue Systems
Session 3 13:40-15:00 -- Dialogue acts and dialogue simulation experiments
S. Lesch, T. Kleinbauer and J. Alexandersson -- Towards a Decent Recognition Rate for the Automatic Classification of a Multidimensional Dialogue Act Tagset
B. McEleney and G. O Hare -- Efficient Dialogue Using a Probabilistic Nested User Model
B. Inouye and A. Biermann -- An Algorithm that Continuously Seeks Minimum Length Dialogs
Session 4 15:30-16:50 -- Automatically learned dialogue policies
J. Henderson, O. Lemon and K. Georgila -- Hybrid Reinforcement/Supervised Learning for Dialogue Policies from COMMUNICATOR data
J. D. Williams, P. Poupart and S. Young -- Factored Partially Observable Markov Decision Processes for Dialogue Management
M. Frampton and O. Lemon -- Reinforcement Learning of Dialogue Strategies using the User's Last Dialogue Act
Session 5 16:50-17:20 -- Discussion
ProceedingsProceedings of the Fourth IJCAI Workshop on Knowledge and Reasoning in Practical Dialogue Systems
Organizing CommitteeIngrid Zukerman (Chair)
School of Computer Science and Software Engineering
Clayton, Victoria 3800, Australia
tel: +61 3 9905-5202
fax: +61 3 9905-5146
Jan Alexandersson (Co-Chair)
Arne Jönsson (Co-Chair)
Program CommitteeJohan Boye, Telia Research, Sweden
Sandra Carberry, University of Delaware, USA
Peter Heeman, Oregon Graduate Institute, USA
Eric Horvitz, Microsoft Research, USA
Kazunori Komatani, Kyoto University, Japan
Staffan Larsson, Göteborgs Universitet, Sweden
Diane Litman, University of Pittsburgh, USA
Michael McTear, University of Ulster, UK
Norbert Reithinger, DFKI, Germany
Candy Sidner, MERL, USA
David Traum, USC Institute for Creative Technology, USA
Related Nearby Events10th International Conference on User Modeling
10th European Workshop on Natural Language Generation