Assigning personality/identity to a chatting machine for coherent conversation generation

TL;DR

This paper presents a novel model for chatbots that generates more coherent and natural responses by incorporating a predefined personality or identity, using specialized modules to detect, select, and utilize profile information.

Contribution

It introduces a new multi-module model that effectively integrates profile information into response generation for more coherent chatbot conversations.

Findings

Model produces more coherent responses

Responses are more natural and diversified

Effective use of social media data for training

Abstract

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.