Empirical Specification of Dialogue Games for an Interactive Agent

This article addresses the challenge of designing the communicative behaviour of an agent interacting with humans. We present a data-driven methodology based on the production of a matrix representation of a corpus from which we extract dialogue patterns. These patterns reflect the minimal units of interaction which turn out to be very attractive for dialogue modelling. We present a framework to specify dialogue games from these patterns based on the notion of social commitments. We exemplify the specification of dialogue games by implementing all the steps of our methodology on a task-oriented corpus. The produced games are validated by showing that they appropriately describe the patterns appearing in a reference corpus.

[1]  Alain Loisel,et al.  A Conversational Agent for Information Retrieval based on a Study of Human Dialogues , 2012, ICAART.

[2]  Harry Bunt,et al.  The DIT++ taxanomy for functional dialogue markup , 2009 .

[3]  Staffan Larsson,et al.  Information state and dialogue management in the TRINDI dialogue move engine toolkit , 2000, Natural Language Engineering.

[4]  Harry Bunt,et al.  Multifunctionality in dialogue , 2011, Comput. Speech Lang..

[5]  Joris Hulstijn,et al.  Dialogue Models for Inquiry and Transaction , 2000 .

[6]  Brahim Chaib-draa,et al.  DIAGAL: An Agent Communication Language Based on Dialogue Games and Sustained by Social Commitments , 2006, Autonomous Agents and Multi-Agent Systems.

[7]  Candace L. Sidner,et al.  COLLAGEN: A Collaboration Manager for Software Interface Agents , 1998, User Modeling and User-Adapted Interaction.

[8]  Staffan Larsson,et al.  Issue-based Dialogue Management , 2002 .

[9]  W. Mann Dialogue games: Conventions of human interaction , 1988 .

[10]  付伶俐 打磨Using Language,倡导新理念 , 2014 .

[11]  Brahim Chaib-draa,et al.  Commitment-based and dialogue-game-based protocols: new trends in agent communication languages , 2002, The Knowledge Engineering Review.

[12]  Munindar P. Singh Social and psychological commitments in multiagent systems , 2011 .

[13]  S J Darmoni,et al.  CISMeF: A Structured Health Resource Guide , 2000, Methods of Information in Medicine.

[14]  Stephen Pulman The TRINDI Project: Some Preliminary Themes , 1998 .

[15]  Candace L. Sidner,et al.  Attention, Intentions, and the Structure of Discourse , 1986, CL.

[16]  Kalina Bontcheva,et al.  Text Processing with GATE , 2011 .

[17]  Z. Alès,et al.  A Methodology to Design Human-Like Embodied Conversational Agents , 2012 .

[18]  R. Cole,et al.  Survey of the State of the Art in Human Language Technology , 2010 .

[19]  Remko Scha,et al.  A Syntactic Approach to Discourse Semantics , 1984, ACL.

[20]  Ian Lewin 2 00 0 A formal model of Conversational Game Theory , 2000 .

[21]  Gheorghe Tecuci,et al.  Seven Aspects of Mixed-Initiative Reasoning: An Introduction to this Special Issue on Mixed-Initiative Assistants , 2007, AI Mag..

[22]  Nicolas Maudet Modéliser les conventions des interactions langagières : la contribution des jeux de dialogue , 2001 .