Leveraging POMDPs trained with user simulations and rule-based dialogue management in a spoken dialogue system

Authors:
Sebastian Varges;Silvia Quarteroni;Giuseppe Riccardi;Alexei V. Ivanov;Pierluigi Roberti
Affiliations:
University of Trento, Povo di Trento, Italy;University of Trento, Povo di Trento, Italy;University of Trento, Povo di Trento, Italy;University of Trento, Povo di Trento, Italy;University of Trento, Povo di Trento, Italy
Venue:
SIGDIAL '09 Proceedings of the SIGDIAL 2009 Conference: The 10th Annual Meeting of the Special Interest Group on Discourse and Dialogue
Year:
2009

Citing 3
Cited 1

A survey of statistical user simulation techniques for reinforcement-learning of dialogue management strategies

The Knowledge Engineering Review
Partially observable Markov decision processes for spoken dialog systems

Computer Speech and Language
Persistent information state in a data-centric architecture

SIGdial '08 Proceedings of the 9th SIGdial Workshop on Discourse and Dialogue

Cooperative user models in statistical dialog simulators

SIGDIAL '10 Proceedings of the 11th Annual Meeting of the Special Interest Group on Discourse and Dialogue

Quantified Score

Hi-index	0.00

Visualization

Abstract

We have developed a complete spoken dialogue framework that includes rule-based and trainable dialogue managers, speech recognition, spoken language understanding and generation modules, and a comprehensive web visualization interface. We present a spoken dialogue system based on Reinforcement Learning that goes beyond standard rule based models and computes on-line decisions of the best dialogue moves. Bridging the gap between handcrafted (e.g. rule-based) and adaptive (e.g. based on Partially Observable Markov Decision Processes - POMDP) dialogue models, this prototype is able to learn high rewarding policies in a number of dialogue situations.