This paper investigates the problem of bootstrapping a statistical dialogue manager without access to training data and proposes a new probabilistic agenda-based method for simulating user behaviour. In experiments with a statistical POMDP dialogue system, the simulator was realistic enough to successfully test the prototype system and train a dialogue policy. An extensive study with human subjects showed that the learned policy was highly competitive, with task completion rates above 90%.
CITATION STYLE
Schatzmann, J., Thomson, B., Weilhammer, K., Ye, H., & Young, S. (2007). Agenda-based user simulation for bootstrapping a POMDP dialogue system. In NAACL-HLT 2007 - Human Language Technology Conference of the North American Chapter of the Association of Computational Linguistics, Companion Volume: Short Papers (pp. 149–152). Association for Computational Linguistics (ACL). https://doi.org/10.3115/1614108.1614146
Mendeley helps you to discover research relevant for your work.