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

A Two-Tier User Simulation Model for Reinforcement Learning of Adaptive Referring Expression Generation Policies Srinivasan Janarthanam author Oliver Lemon author 2009-09 text Proceedings of the SIGDIAL 2009 Conference Patrick Healey editor Roberto Pieraccini editor Donna Byron editor Steve Young editor Matthew Purver editor Association for Computational Linguistics London, UK conference publication janarthanam-lemon-2009-two https://aclanthology.org/W09-3916/ 2009-09 120 123