Finding Appropriate Interaction Strategies for Proactive Dialogue Systems—An Open Quest

In this paper we elucidate the challenges of proactiveness in dialogue systems and how these influence the effectiveness of turn-taking behaviour in multimodal as well as in unimodal dialogue systems. Effective turn-taking is essential for a natural and qualitatively high humancomputer interaction. Especially in spoken dialogue systems, analysing whether the dialogue system should or could take the floor, seems to be an important process in the overall perceived quality of the interaction. Additionally, as technical systems get increasingly complex and evolve in the direction of intelligent assistants rather than simple problem solvers, proactive system behaviour may influence the perception of the ongoing dialogue between human and computer. Autonomously made decisions or triggered system actions may surprise or even disturb the user, which may result in a reduced transparency of the technical system. Therefore, the decision if, when and how to take the floor in a proactive system yields additional challenges. We discuss each layer of decision-making and explain how multimodal cognitive systems can help to control this decision-making in a valuable fashion.

[1]  S. Duncan,et al.  Some Signals and Rules for Taking Speaking Turns in Conversations , 1972 .

[2]  Bonnie M. Muir,et al.  Trust in automation. I: Theoretical issues in the study of trust and human intervention in automated systems , 1994 .

[3]  Ben Shneiderman,et al.  Split menus: effectively using selection frequency to organize menus , 1994, TCHI.

[4]  Jörg Cassens,et al.  Explanation Goals in Case-Based Reasoning , 2004 .

[5]  David G. Novick,et al.  Root causes of lost time and user stress in a simple dialog system , 2005, INTERSPEECH.

[6]  Maxine Eskénazi,et al.  Doing research on a deployed spoken dialogue system: one year of let's go! experience , 2006, INTERSPEECH.

[7]  Lorenza Mondada,et al.  Multimodal resources for turn-taking , 2007 .

[8]  Zhihong Zeng,et al.  A Survey of Affect Recognition Methods: Audio, Visual, and Spontaneous Expressions , 2009, IEEE Trans. Pattern Anal. Mach. Intell..

[9]  Julia Hirschberg,et al.  Turn-taking cues in task-oriented dialogue , 2011, Comput. Speech Lang..

[10]  Susanne Biundo-Stephan,et al.  Advanced user assistance based on AI planning , 2011, Cognitive Systems Research.

[11]  Maxine Eskénazi,et al.  Optimizing the turn-taking behavior of task-oriented spoken dialog systems , 2012, TSLP.

[12]  Sidney K. D'Mello,et al.  Consistent but modest: a meta-analysis on unimodal and multimodal affect detection accuracies from 30 studies , 2012, ICMI '12.

[13]  Gregor Bertrand,et al.  Companion-Technology: Towards User- and Situation-Adaptive Functionality of Technical Systems , 2014, 2014 International Conference on Intelligent Environments.

[14]  Wolfgang Minker,et al.  Justification and Transparency Explanations in Dialogue Systems to Maintain Human-Computer Trust , 2014, IWSDS.

[15]  Wolfgang Minker,et al.  Probabilistic Human-Computer Trust Handling , 2014, SIGDIAL Conference.

[16]  E. Schegloff,et al.  A simplest systematics for the organization of turn-taking for conversation , 2015 .