TERG: Topic-Aware Emotional Response Generation for Chatbot

Pei Huo, Yan Yang, Jie Zhou, Chengcai Chen, Liang He

Abstract: A more intelligent chatbot should be able to express emotion, in addition to providing informative responses. Despite much works in designing neural dialogue generation systems in recent years, few studies consider both emotion to be expressed and topic relevance in the generation process. To address this problem, we present a Topic-aware Emotional Response Generation (TERG) model, which can not only exactly generate desired emotional response but perform well in topic relevance. Specifically, TERG equips an encoder-decoder structure with an emotion aware module to control the emotional sentence generation and a topic aware module to enhance topic relevance. We evaluate our model on a large real-world dataset of conversations from social media. Experimental results show that our model obtains a significant improvement against several strong baseline methods on both automatic and human evaluation.