Paper: Policy Learning for Domain Selection in an Extensible Multi-domain Spoken Dialogue System

ACL ID D14-1007
Title Policy Learning for Domain Selection in an Extensible Multi-domain Spoken Dialogue System
Venue Conference on Empirical Methods in Natural Language Processing
Session Main Conference
Year 2014
Authors

This paper proposes a Markov Decision Process and reinforcement learning based approach for domain selection in a multi- domain Spoken Dialogue System built on a distributed architecture. In the proposed framework, the domain selection prob- lem is treated as sequential planning in- stead of classification, such that confir- mation and clarification interaction mech- anisms are supported. In addition, it is shown that by using a model parameter ty- ing trick, the extensibility of the system can be preserved, where dialogue com- ponents in new domains can be easily plugged in, without re-training the domain selection policy. The experimental results based on human subjects suggest that the proposed model marginally outperforms a non-trivial baseline.