Conversation as Action Under Uncertainty

TL;DR

This paper presents Quartet, a multimodal architecture for robust spoken dialogue that models conversation as inference and decision-making under uncertainty, demonstrated through two prototype systems.

Contribution

It introduces four levels of analysis and associated inference and decision strategies for managing uncertainties in multimodal dialogue systems.

Findings

Successful implementation of Quartet in prototype systems

Enhanced robustness in spoken dialogue management

Effective handling of uncertainties in multimodal interactions

Abstract

Conversations abound with uncetainties of various kinds. Treating conversation as inference and decision making under uncertainty, we propose a task independent, multimodal architecture for supporting robust continuous spoken dialog called Quartet. We introduce four interdependent levels of analysis, and describe representations, inference procedures, and decision strategies for managing uncertainties within and between the levels. We highlight the approach by reviewing interactions between a user and two spoken dialog systems developed using the Quartet architecture: Prsenter, a prototype system for navigating Microsoft PowerPoint presentations, and the Bayesian Receptionist, a prototype system for dealing with tasks typically handled by front desk receptionists at the Microsoft corporate campus.