skip to main content
Language:
Search Limited to: Search Limited to: Resource type Show Results with: Show Results with: Search type Index

Evaluation of a hierarchical reinforcement learning spoken dialogue system

Computer speech & language, 2010-04, Vol.24 (2) [Peer Reviewed Journal]

Distributed under a Creative Commons Attribution 4.0 International License ;ISSN: 0885-2308 ;EISSN: 1095-8363 ;DOI: 10.1016/j.csl.2009.07.001

Digital Resources/Online E-Resources

Citations Cited by
  • Title:
    Evaluation of a hierarchical reinforcement learning spoken dialogue system
  • Author: Cuayáhuitl, Heriberto ; Renals, Steve ; Lemon, Oliver ; Shimodaira, Hiroshi
  • Is Part Of: Computer speech & language, 2010-04, Vol.24 (2)
  • Description: We describe an evaluation of spoken dialogue strategies designed using hierarchical reinforcement learning agents. The dialogue strategies were learnt in a simulated environment and tested in a laboratory setting with 32 users. These dialogues were used to evaluate three types of machine dialogue behaviour: hand-coded, fully-learnt and semi-learnt. These experiments also served to evaluate the realism of simulated dialogues using two proposed metrics contrasted with 'precision-recall'. The learnt dialogue behaviours used the Semi-Markov Decision Process (SMDP) model, and we report the first evaluation of this model in a realistic conversational environment. Experimental results in the travel planning domain provide evidence to support the following claims: (a) hierarchical semi-learnt dialogue agents are a better alternative (with higher overall performance) than deterministic or fully-learnt behaviour; (b) spoken dialogue strategies learnt with highly coherent user behaviour and conservative recognition error rates (keyword error rate of 20%) can outperform a reasonable hand-coded strategy; and (c) hierarchical reinforcement learning dialogue agents are feasible and promising for the (semi) automatic design of optimized dialogue behaviours in larger-scale systems.
  • Publisher: Elsevier
  • Language: English
  • Identifier: ISSN: 0885-2308
    EISSN: 1095-8363
    DOI: 10.1016/j.csl.2009.07.001
  • Source: Hyper Article en Ligne (HAL) (Open Access)
Back to results list
Go to Previous pagePrevious Result  5 NextGo to Next page
INSPIRE LIBRARY - TON DUC THANG UNIVERSITY (84-028) 37 755 057 Feedback
19 Nguyen Huu Tho St. Dist.7, HCM thuvien@tdtu.edu.vn

Copyright © 2017 INSPIRE LIBRARY - TON DUC THANG UNIVERSITY

Searching Remote Databases, Please Wait