Assigning personality/identity to a chatting machine for coherent conversation generation
This addresses the challenge of making chatbots more realistic and natural for users, though it appears incremental as it builds on existing conversation generation methods.
The paper tackled the problem of generating chatbot responses coherent with a pre-specified personality or identity profile, and the result showed that the model produced more coherent, natural, and diversified responses as validated by manual and automatic evaluations.
Endowing a chatbot with personality or an identity is quite challenging but critical to deliver more realistic and natural conversations. In this paper, we address the issue of generating responses that are coherent to a pre-specified agent profile. We design a model consisting of three modules: a profile detector to decide whether a post should be responded using the profile and which key should be addressed, a bidirectional decoder to generate responses forward and backward starting from a selected profile value, and a position detector that predicts a word position from which decoding should start given a selected profile value. We show that general conversation data from social media can be used to generate profile-coherent responses. Manual and automatic evaluation shows that our model can deliver more coherent, natural, and diversified responses.