banner

8th WORKSHOP ON KNOWLEDGE AND REASONING IN PRACTICAL DIALOGUE SYSTEMS

Extended deadline for submissions: May 10

The eighth IJCAI workshop on ''Knowledge and Reasoning in Practical Dialogue Systems'' will focus on challenges arising due to comprehension difficulties in dialogue systems. These difficulties include speech recognition errors and speech disfluencies in spoken dialogue systems, syntax errors, out-of-grammar and out-of-vocabulary phenomena, rambling discourse, as well as non-cooperative dialogues. Topics addressed in the workshop include, but are not limited to, the following:

  • Approaches for identifying different types of comprehension difficulties, ranging from mis-hearing to uncooperative interlocutors. In particular, how does a dialogue system determine how well it has understood an utterance?
  • Approaches for addressing these difficulties, eg correcting likely hearing problems, learning unknown words, and asking clarification questions.
  • How different types of comprehension difficulties interact with different parts of a dialogue system, eg interpretation, dialogue strategy, and response generation.
  • Robustness when faced with unpredictability and comprehension difficulties.
  • How can we implement dialogue systems that take into consideration their environment? What is the role of the environment in addressing comprehension difficulties?
  • What are the most appropriate ways to evaluate dialogue systems for different applications and situations. In particular, how does one evaluate robustness when faced with comprehension difficulties?

This is the eighth IJCAI workshop on ''Knowledge and Reasoning in Practical Dialogue Systems''. 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 the fourth workshop was held at IJCAI-2005 at Edinburgh. The fifth workshop was held in Hyderabad, India, 2007 and focused on dialogue systems for robots and virtual humans. The sixth workshop was held in Pasadena, CA in 2009, and focussed on challenges of novel applications of practical dialogue systems. and the seventh workshop, held in Barcelona, Spain, in 2011, considered dialogue systems for different types of users, such as elderly people and people with special needs.

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. The topic is particularly timely, as dialogue systems, in particular spoken ones, are ready to progress from toy or restricted systems, to more open-ended applications. As the applications become more complex, so does the potential for comprehension difficulties, which must be robustly handled.

The workshop should also be of interest to anyone studying dialogue and multimodal interfaces. The proposed workshop emphasizes practical research, eg empirical evaluations, formalization of dialogue phenomena, and development of intelligent interfaces for various applications.

As with the previous workshops in the series, we expect a benefit from informal, high quality interactions between those interested and involved in developing practical dialogue systems, including sharing of techniques and experiences. Additionally, the theme of comprehension difficulties is expected to attract participation from industry, as this is a common problem in dialogue systems ranging from triage and slot-filling systems to virtual reality systems. Further, it is worth noting that while there has been a fair amount of recent work in (spoken) dialogue system, to our knowledge there has not been a recent workshop that focuses on comprehension difficulties (since Error Handling in Spoken Dialogue Systems, August 28-31, 2003 Chateau d'Oex, Vaud, Switzerland).

Workshop format

The workshop will be kept small, a one day workshop 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. We also encourage contributions of a critical or comparative nature that provide fuel for discussion, and invite people to share their experiences of implementing and coordinating knowledge modules in their dialogue systems, and integrating dialogue components with other applications. Further, we hope to have contributions which focus on the challenges of Chinese dialogue systems.

Important dates

  • April 20, 2013 - Submission of contributions to workshop
  • May 20, 2013 - Workshop paper acceptance notification
  • May 30, 2013 - Deadline for final camera ready copy to workshop organizers
  • May 10, 2013 - Submission of contributions to workshop
  • June 3, 2013 - Workshop paper acceptance notification
  • June 10, 2013 - Deadline for final camera ready copy to workshop organizers
  • August 3, 2013 - Workshop

Submissions

Papers may be any of the following types:
  • Regular Papers papers of length 6-12 pages, for regular presentation
  • Short Papers with brief results, or position papers, of length up to 6 pages.
Papers should include authors names and affiliation and full references (not anonymous submission). All papers should be formatted according to the AAAI formats: AAAI Press Author Instructions

Submission procedure

Papers should be submitted by web by registering at the following address: http://www.easychair.org/conferences/?conf=krpds2013

Organizing Committee

Jan Alexandersson (Co-chair)
German Research Center for Artificial Intelligence, DFKI GmbH, Germany
email: janal@dfki.de

Arne Jönsson (Co-Chair)
Department of Computer and Information Science, Linköping University, Sweden
email: arnjo@ida.liu.se

David Traum (Co-Chair)
Institute for Creative Technologies, University of Southern California, USA
email: traum@ict.usc.edu

Ingrid Zukerman (Chair)
Faculty of Information Technology, Monash University, Australia
email: Ingrid.Zukerman@monash.edu

Programme committee

Dan Bohus, Microsoft Research, USA
Sandra Carberry, University of Delaware, USA
Lawrence Cavedon, NICTA and RMIT, Australia
Jens Edlund, Royal Technical Institute (KTH), Sweden
Maxine Eskenazi, Carnegie Mellon University, USA
Alex Chengyu Fang, The City University of Hong Kong, China
Kallirroi Georgila, University of Southern California, USA
Thomas Kleinbauer, Monash University, Australia
Kazunori Komatani, Nagoya University, Japan
Diane Litman, University of Pittsburgh, USA
Kathleen McCoy, University of Delaware, USA
Helen Meng, The Chinese University of Hong Kong, China
Wolfgang Minker, Universitat Ulm, Germany
Mikio Nakano, Honda Research Institute, Japan
Rebecca Passonneau, Columbia University, USA
Olivier Pietquin, Supelec, France
Norbert Reithinger, DFKI, Germany
Candace Sidner, Sidner Consulting, USA
Gabriel Skanze, Royal Technical Institute (KTH), Sweden
Jason Williams, Microsoft Research, USA