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

Zhuoran Wang, Hongliang Chen, Guanchun Wang, Hao Tian, Hua Wu, Haifeng Wang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

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 problem is treated as sequential planning instead of classification, such that confirmation and clarification interaction mechanisms are supported. In addition, it is shown that by using a model parameter tying trick, the extensibility of the system can be preserved, where dialogue components 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.
Original languageEnglish
Title of host publicationProceedings of EMNLP 2014
Subtitle of host publicationConference on Empirical Methods in Natural Language Processing
PublisherAssociation for Computational Linguistics
Publication statusAccepted/In press - 2014
Event2014 Conference on Empirical Methods in Natural Language Processing - Doha, Qatar
Duration: 25 Oct 201429 Oct 2014

Conference

Conference2014 Conference on Empirical Methods in Natural Language Processing
Abbreviated titleEMNLP 2014
Country/TerritoryQatar
CityDoha
Period25/10/1429/10/14

Fingerprint

Dive into the research topics of 'Policy Learning for Domain Selection in an Extensible Multi-domain Spoken Dialogue System'. Together they form a unique fingerprint.

Cite this