Evaluation of a hierarchical reinforcement learning spoken dialogue system

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 `PrecisionRecall'. 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 ...

• Type: Journal
• Year: 2010
• Where: CSL
• Authors: Heriberto Cuayáhuitl, Steve Renals, Oliver Lemon, Hiroshi Shimodaira
• Keywords: Automated Reasoning, CSL 2010, Dialogue, Dialogue Strategies, Spoken Dialogue Strategies