TY - GEN
T1 - A user simulator architecture for socially-aware conversational agents
AU - Jain, Alankar
AU - Pecune, Florian
AU - Matsuyama, Yoichi
AU - Cassell, Justine
N1 - Funding Information:
This work was supported in part by generous funding from Microsoft, LivePerson, Google, and the IT R&D program of MSIP/IITP [2017-0-00255, Autonomous Digital Companion Development]. We would also like to thank all the members of Articulab in Carnegie Mellon University for their useful feedback.
Publisher Copyright:
© 2018 Copyright held by the owner/author(s).
PY - 2018/11/5
Y1 - 2018/11/5
N2 - Over the last two decades, Reinforcement Learning (RL) has emerged the method of choice for data-driven dialog management. However, one of the limitations of RL methods for the optimization of dialog managers in the context of virtual conversational agents, is that they require a large amount of data, which is often unavailable, particularly when the dialog deals with complex discourse phenomena. User simulators help address this problem by generating synthetic data to train RL agents in an online fashion. In this work, we extend user simulators to the case of socially-aware conversational agents, that combine task and social functions. We propose a novel architecture that takes into consideration the user’s conversational goals and generates both task and social behaviour. Our proposed architecture is general enough to be useful for training socially-aware conversational agents in any domain. As a proof of concept, we construct a user simulator for training a conversational recommendation agent and provide evidence towards the effectiveness of the approach.
AB - Over the last two decades, Reinforcement Learning (RL) has emerged the method of choice for data-driven dialog management. However, one of the limitations of RL methods for the optimization of dialog managers in the context of virtual conversational agents, is that they require a large amount of data, which is often unavailable, particularly when the dialog deals with complex discourse phenomena. User simulators help address this problem by generating synthetic data to train RL agents in an online fashion. In this work, we extend user simulators to the case of socially-aware conversational agents, that combine task and social functions. We propose a novel architecture that takes into consideration the user’s conversational goals and generates both task and social behaviour. Our proposed architecture is general enough to be useful for training socially-aware conversational agents in any domain. As a proof of concept, we construct a user simulator for training a conversational recommendation agent and provide evidence towards the effectiveness of the approach.
KW - Conversational agent
KW - Dialog system
KW - Rapport
KW - User simulator
UR - http://www.scopus.com/inward/record.url?scp=85058453593&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85058453593&partnerID=8YFLogxK
U2 - 10.1145/3267851.3267916
DO - 10.1145/3267851.3267916
M3 - Conference contribution
AN - SCOPUS:85058453593
T3 - Proceedings of the 18th International Conference on Intelligent Virtual Agents, IVA 2018
SP - 133
EP - 140
BT - Proceedings of the 18th International Conference on Intelligent Virtual Agents, IVA 2018
PB - Association for Computing Machinery, Inc
T2 - 18th ACM International Conference on Intelligent Virtual Agents, IVA 2018
Y2 - 5 November 2018 through 8 November 2018
ER -