论文信息 - A research platform for multi-agent dialogue dynamics

A research platform for multi-agent dialogue dynamics

Dialogue agents are often designed with the tacit assumption that at any time, there is only one agent and one human, and that their communication channel is exclusive. We are interested in evaluating complications that arise when multiple heterogeneous dialogue agents interact with one or more human interlocutors, and their communication channel is necessarily shared. In This work we describe a multi-agent dialogue test-bed that we have implemented to study such dialogue coordination issues. We also describe an initial pilot study that uses this test-bed to experiment with a very simple addressee disambiguation algorithm.

[1] J M Wilentz,et al. Let there be light. , 1976, The Journal of the Florida Medical Association.

[2] Paul Taylor,et al. Festival Speech Synthesis System , 1998 .

[3] Mei-Yuh Hwang,et al. The SPHINX-II speech recognition system: an overview , 1993, Comput. Speech Lang..

[4] Jonathan J. Cadiz,et al. "Let There Be Light": Examining Interfaces for Homes of the Future , 2001, INTERACT.

[5] Alexander I. Rudnicky,et al. Ravenclaw: dialog management using hierarchical task decomposition and an expectation agenda , 2003, INTERSPEECH.

[6] Victor Zue,et al. GALAXY-II: a reference architecture for conversational system development , 1998, ICSLP.

[7] Alexander I. Rudnicky,et al. Stochastic Language Generation for Spoken Dialogue Systems , 2000 .

[8] Alexander I. Rudnicky,et al. Integrating Multiple Knowledge Sources for Utterance-Level Confidence Annotation in the CMU Communicator Spoken Dialog System , 2002 .