Using a Bayesian model of the listener to unveil the dialogue information state

Communicative listener feedback is a prevalent coordination mechanism in dialogue. Listeners use feedback to provide evidence of understanding to speakers, who, in turn, use it to reason about the listeners' mental state of listening, determine the groundedness of communicated information, and adapt their subsequent utterances to the listeners' needs. We describe a speaker-centric Bayesian model of listeners and their feedback behaviour, which can interpret the listener's feedback signal in its dialogue context and reason about the listener's mental state as well as the grounding status of objects in information state.

[1]  Illtyd Trethowan.  Causality , 1938 .

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

[3]  J. Pearl.  Causality: Models, Reasoning and Inference , 2000 .

[4]  Eric Horvitz,et al.  Conversation as Action Under Uncertainty , 2000, UAI.

[5]  H. H. Clark,et al.  Speaking while monitoring addressees for understanding , 2004 .

[6]  Alex Lascarides,et al.  Logics of Conversation , 2005, Studies in natural language processing.

[7]  Stefan Kopp,et al.  Modeling Embodied Feedback with Virtual Humans , 2006, ZiF Workshop.

[8]  Nigel Ward,et al.  Non-lexical conversational sounds in American English , 2006 .

[9]  Stefan Kopp,et al.  Synthesis of prosodic attitudinal variants in German backchannel ja , 2007, INTERSPEECH.

[10]  Harry Bunt,et al.  Evaluating Dialogue Act Tagging with Naive and Expert Annotators , 2008, LREC.

[11]  David R. Traum,et al.  Degrees of Grounding Based on Evidence of Understanding , 2008, SIGDIAL Workshop.

[12]  Adnan Darwiche,et al.  Modeling and Reasoning with Bayesian Networks , 2009 .

[13]  Olivier Pietquin,et al.  Simulation of the Grounding Process in Spoken Dialog Systems with Bayesian Networks , 2010, IWSDS.

[14]  S. Brennan,et al.  Attenuating Information in Spoken Communication: For the Speaker, or for the Addressee?. , 2010 .

[15]  Matthew Stone,et al.  Coherence and Rationality in Grounding , 2010 .

[16]  Stefan Kopp,et al.  Towards Conversational Agents That Attend to and Adapt to Communicative User Feedback , 2011, IVA.

[17]  Sathish Pammi.  Synthesis of listener vocalizations: towards interactive speech synthesis , 2011 .

[18]  David Barber,et al.  Bayesian reasoning and machine learning , 2012 .

[19]  Stefan Kopp,et al.  Combining Incremental Language Generation and Incremental Speech Synthesis for Adaptive Information Presentation , 2012, SIGDIAL Conference.

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