A special session has been approved. Its title is Chatbots and Conversational Agents and Dialogue Breakdown Detection Challenge
(WOCHAT+DBDC).
Organisers
Special Session organising Committee
- Rafael E. Banchs, Nanyang Technological University, Singapore
- Ron Artstein, University of Southern California, USA
- Verena Rieser, Heriot-Watt University, UK
- Zhou Yu, University of California, Davis, USA
Dialogue Breakdown Detection organizing Committee
- Ryuichiro Higashinaka, Nippon Telegraph and Telephone Corporation, Japan
- Luis F. D’Haro, Technical University of Madrid, Spain
- Bayan Abu Shawar, Arab Open University, Jordan
WOCHAT Steering Committee
- Joseph Mariani, LIMSI-CNRS, France
- David Traum, University of Southern California, USA
- Alexander Rudnicky, Carnegie Mellon University, USA
- Haizhou Li, National University of Singapore, Singapore
Program committee members
- Björn Schuller, Imperial College London, UK
- David Suendermann, Educational Testing Service (ETS), USA
- Dilek Hakkani-Tur, Microsoft Research, USA
- Elnaz Nouri, ObEN, USA
- Gabriel Skantze, KTH Royal Institute of Technology, Sweden
- Haizhou Li, Institute for Infocomm Research, Singapore
- Jason Williams, Apple, USA
- Jiang Ridong, Agency for Science, Technology and Research, Singapore
- Justine Cassell, Carnegie Mellon University, USA
- Kristiina Jokinen, University of Helsinki, Finland
- Kotaro Funakoshi, Honda Research Institute, Japan
- Laurence Devillers, LIMSI-CNRS, France
- Luis Fernando D’Haro, Technical University of Madrid, Spain
- Luisa Coheur, Lisbon University, Portugal
- Matthew Henderson,PolyAI, Singapore
- Michael McTear, University of Ulster, UK
- Mikio Nakano, Honda Research Institute, Japan
- Nick Campbell, Trinity College Dublin, Ireland
- Oliver Lemon, Heriot-Watt University, UK
- Ramón López-Cózar, University of Granada, Spain
- Sakriani Sakti, Nara Institute of Science and Technology, Japan
- Satoshi Nakamura, Nara Institute of Science and Technology, Japan
- Seokhwan Kim, Adobe, USA
- Sophie Rosset, LIMSI-CNRS, France
- Stefan Ultes, Cambridge University, UK
- Suraj Nair, Technische Universität München, Germany
- Teruhisa Misu, Honda Research Institute, USA
- Tomoki Toda, Nara Institute of Science and Technology, Japan
- Yasuharu Den, Chiba University, Japan
- Shiv Vitaladevuni, Amazon, USA
Objectives and topics of interest
Although chat-oriented dialogue systems have existed for many years (almost fifty years if we consider Weizenbaum’s Eliza as the starting milestone), they have recently been gaining increasing popularity in
both research and commercial arenas. From the commercial stand point, chat-oriented dialogue seems to be providing an excellent means to engage users for entertainment purposes, as well as to give a more human-like appearance to established vertical goal-oriented dialogue systems.
From the research perspective, on the other hand, this kind of systems poses interesting challenges and problems to the research community. The main objective of this special session and challenge is to bring together researchers working on problems related to chat-oriented dialogue for promoting discussion and knowledge sharing about the state-of-the-art and novel techniques in this field, including data collections, resources and new evaluation protocols for future research.
The session will focus on original research contributions on all aspects of chat-oriented dialogue, including closely related areas such as knowledge representation and reasoning, language generation, and natural language understanding, among others. The session will invite papers in areas including (but not restricted to): chat-oriented dialogue systems, data collections and resources, information extraction, natural language understanding and generation, general domain knowledge representation,
common sense and reasoning, emotion detection and generation, sense of humor detection and generation, user studies and system evaluation.
A shared task will be included along with the special session. In this new edition, the original shared task in the workshop series will be integrated into the Dialogue Breakdown Detection Challenge series, as a combined effort to continue research and exploration on evaluation metrics for dialogue quality at the turn level.