Evaluation of a hierarchical reinforcement learning spoken dialogue system - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue Computer Speech and Language Année : 2010

Evaluation of a hierarchical reinforcement learning spoken dialogue system

Heriberto Cuayáhuitl
  • Fonction : Auteur correspondant
  • PersonId : 907886

Connectez-vous pour contacter l'auteur
Steve Renals
  • Fonction : Auteur
Oliver Lemon
  • Fonction : Auteur
Hiroshi Shimodaira
  • Fonction : Auteur

Résumé

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.
Fichier principal
Vignette du fichier
PEER_stage2_10.1016%2Fj.csl.2009.07.001.pdf (2.68 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-00614845 , version 1 (17-08-2011)

Identifiants

Citer

Heriberto Cuayáhuitl, Steve Renals, Oliver Lemon, Hiroshi Shimodaira. Evaluation of a hierarchical reinforcement learning spoken dialogue system. Computer Speech and Language, 2010, 24 (2), pp.395. ⟨10.1016/j.csl.2009.07.001⟩. ⟨hal-00614845⟩

Collections

PEER
40 Consultations
169 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More