A Two-Tier User Simulation Model for Reinforcement Learning of Adaptive Referring Expression Generation Policies

Srinivasan Janarthanam, Oliver Lemon. A Two-Tier User Simulation Model for Reinforcement Learning of Adaptive Referring Expression Generation Policies. In Patrick G. T. Healey, Roberto Pieraccini, Donna K. Byron, Steve Young, Matthew Purver, editors, Proceedings of the SIGDIAL 2009 Conference, The 10th Annual Meeting of the Special Interest Group on Discourse and Dialogue, 11-12 September 2009, London, UK. pages 120-123, The Association for Computer Linguistics, 2009. [doi]

Abstract

Abstract is missing.