Entrainable Neural Conversation Model Based on Reinforcement Learning

The synchronization of words in conversation, called entrainment, is generally observed in human-human conversations. Entrainment has a high correlation with dialogue success, naturalness, and engagement. In this article, we define entrainment scores based on the word similarities in semantic space to evaluate the entrainment of system generation. We optimized a neural conversation model to the entrainment scores using reinforcement learning so that the system can control the degree of entrainment of the system response. Experimental results showed that the proposed entrainable neural conversation model generated comparable or more natural responses than conventional models and satisfactorily controlled the degree of entrainment of the generated responses.