[3Rin4] Interactive 1

[3Rin4-29] Toward Entrained Response Generation for Neural Conversation Model

〇Seiya Kawano¹, Masahiro Mizukami², Koichiro Yoshino¹, Satoshi Nakamura¹ (1.Nara Institute of Science and Technology, 2.NTT Communication Science Laboratory)

Keywords:Dialogue System, Neural Conversation Model, Entrainment Phenomenon, Reinforcement Learning

Synchronization of words in conversation, called entrainment, is generally observed in human-human conversation. It is reported that entrainment has a high correlation with dialogue engagement. In this work, we consider using several entrainment scores based on the word, co-occurrence to evaluate the entrainment of system generation. We try to build a neural conversation model optimized for these entrainment scores by using reinforcement learning. Experimental results showed that the proposed neural conversation model optimized by the entrainment scores achieved a better entrainment score than general neural conversation models.