Empirical Evaluation of a Reinforcement Learning Spoken Dialogue System
Speaker: Satinder Singh , ATT Labs
Date: September 21 2000
Empirical Evaluation of a Reinforcement Learning Spoken Dialogue System Satinder Singh ATT Labs September 21, 2000 4:00pm refreshments at 3:45pm NE43 - 9th Floor Playroom abstract Spoken dialogue systems communicate with users via automatic speech recognition (ASR) and text-to-speech (TTS) interfaces, and typically mediate the user's access to a back-end database. Designers of such systems face a number of nontrivial choices in dialogue strategy, including user vs. system initiative (the choice between accepting relatively open-ended vs. constrained user utterances), and choices in confirmation strategy (when to confirm or re-prompt for an ambiguous utterance). System design has typically been done in an ad-hoc manner, with subsequent improvements to dialogue strategy being fielded sequentially.
In this work, we apply the formalism of Markov decision processes (MDPs) and the algorithms of reinforcement learning to the problem of automated dialogue strategy synthesis. In this approach, an MDP is built from training data gathered from an initial "exploratory" system. This MDP provides a state-based statistical model of user reactions to system actions, and is used to simultaneously evaluate many dialogue strategies and choose the apparent optimal among them. At AT&T Labs, we have applied this methodology in a dialogue system for accessing a database of information on activities in New Jersey, and have run controlled user experiments to evaluate the approach. In this talk, I will describe our results, which include statistically significant improvements in system performance, and discuss the issues we faced in making the methodology work.
This is joint work with Michael Kearns, Diane Litman and Marilyn Walker
See other events that are part of AI Colloquium Series Fall 2000
See other events happening in September 2000