Incremental interpretation and prediction of utterance meaning for interactive dialogue

We present techniques for the incremental interpretation and prediction of utterance meaning in dialogue systems. These techniques open possibilities for systems to initiate responsive overlap behaviors during user speech, such as interrupting, acknowledging, or completing a user's utterance while it is still in progress. In an implemented system, we show that relatively high accuracy can be achieved in understanding of spontaneous utterances before utterances are completed. Further, we present a method for determining when a system has reached a point of maximal understanding of an ongoing user utterance, and show that this determination can be made with high precision. Finally, we discuss a prototype implementation that shows how systems can use these abilities to strategically initiate system completions of user utterances. More broadly, this framework facilitates the implementation of a range of overlap behaviors that are common in human dialogue, but have been largely absent in dialogue systems.

[1]  H. H. Clark Arenas of language use , 1993 .

[2]  David Traum,et al.  Semantics and Pragmatics of Questions and Answers for Dialogue Agents , 2003 .

[3]  David DeVault,et al.  Interpretation of Partial Utterances in Virtual Human Dialogue Systems , 2010, NAACL.

[4]  Munindar P. Singh,et al.  Conversational Agents , 1997 .

[5]  J. Cassell,et al.  Embodied conversational agents , 2000 .

[6]  David R. Traum,et al.  Multi-party, Multi-issue, Multi-strategy Negotiation for Multi-modal Virtual Agents , 2008, IVA.

[7]  David Schlangen,et al.  Comparing Local and Sequential Models for Statistical Incremental Natural Language Understanding , 2010, SIGDIAL Conference.

[8]  H. H. Clark,et al.  Collaborating on contributions to conversations , 1987 .

[9]  V. Yngve On getting a word in edgewise , 1970 .

[10]  David Schlangen,et al.  Incremental Reference Resolution: The Task, Metrics for Evaluation, and a Bayesian Filtering Model that is Sensitive to Disfluencies , 2009, SIGDIAL Conference.

[11]  C. Goodwin The Interactive Construction of a Sentence in Natural Conversation , 1979 .

[12]  Jeff Rickel,et al.  Virtual Humans for Team Training in Virtual Reality , 1999 .

[13]  Stacy Marsella,et al.  Nonverbal Behavior Generator for Embodied Conversational Agents , 2006, IVA.

[14]  Philip R. Cohen,et al.  Referring as a Collaborative Process , 2003 .

[15]  Joakim Nivre,et al.  On the Semantics and Pragmatics of Linguistic Feedback , 1992, J. Semant..

[16]  Alexander I. Rudnicky,et al.  Pocketsphinx: A Free, Real-Time Continuous Speech Recognition System for Hand-Held Devices , 2006, 2006 IEEE International Conference on Acoustics Speech and Signal Processing Proceedings.

[17]  David DeVault,et al.  Towards Natural Language Understanding of Partial Speech Recognition Results in Dialogue Systems , 2009, HLT-NAACL.

[18]  David DeVault,et al.  Can I Finish? Learning When to Respond to Incremental Interpretation Results in Interactive Dialogue , 2009, SIGDIAL Conference.

[19]  David R. Traum,et al.  A Common Ground for Virtual Humans: Using an Ontology in a Natural Language Oriented Virtual Human Architecture , 2008, LREC.

[20]  Seiji Yamada,et al.  Non-humanlike Spoken Dialogue: A Design Perspective , 2010, SIGDIAL Conference.

[21]  Adam L. Berger,et al.  A Maximum Entropy Approach to Natural Language Processing , 1996, CL.

[22]  Gabriel Skantze,et al.  Incremental Dialogue Processing in a Micro-Domain , 2009, EACL.

[23]  Susan McRoy,et al.  Detecting, Repairing, and Preventing Human-Machine Miscommunication (Workshop Report) , 1997, AI Mag..

[24]  Nick Hawes,et al.  Incremental , multi-level processing for comprehending situated dialogue in human-robot interaction , 2007 .

[25]  Jens Allwood,et al.  An activity-based approach to pragmatics , 2000, Abduction, Belief and Context in Dialogue.

[26]  David DeVault,et al.  Making Grammar-Based Generation Easier to Deploy in Dialogue Systems , 2008, SIGDIAL Workshop.

[27]  Stacy Marsella,et al.  A domain-independent framework for modeling emotion , 2004, Cognitive Systems Research.

[28]  James F. Allen,et al.  Incremental Dialogue System Faster than and Preferred to its Nonincremental Counterpart , 2007 .

[29]  Gabriel Skantze,et al.  A General, Abstract Model of Incremental Dialogue Processing , 2011 .

[30]  Massimo Poesio,et al.  Completions, Coordination, and Alignment in Dialogue , 2010, Dialogue Discourse.

[31]  E. Schegloff,et al.  A simplest systematics for the organization of turn-taking for conversation , 1974 .

[32]  Yukiko I. Nakano,et al.  Towards a Model of Face-to-Face Grounding , 2003, ACL.