Incorporating emotion for response generation in multi-turn dialogues

• Published in: Applied intelligence (Dordrecht, Netherlands) Netherlands), 2022-05, Vol.52 (7), p.7218-7229
• Main Authors: Mao, Yanying, Cai, Fei, Guo, Yupu, Chen, Honghui
• Format: Article
• Language: English
• Subjects: Artificial Intelligence; Coders; Computer Science; Context; Datasets; Emotions; Encoders-Decoders; Machines; Manufacturing; Mechanical Engineering; Processes
• ISSN: 0924-669X; 1573-7497
• DOI: 10.1007/s10489-021-02819-z

Generating semantically and emotionally context-consistent responses is key to intelligent dialogue systems. Previous works mainly refer to the context in the dialogue history to generate semantically related responses, ignoring the potential emotion in the conversation. In addition, existing methods mainly fail to consider the emotional changes of interlocutors and emotional categories simultaneously. However, emotion is crucial to reflect the interlocutor’s intent. In this paper, we propose an Emotion Capture Chat Machine (ECCM) that is able to capture the explicit and underlying emotional signal in the context to generate appropriate responses. In detail, we design a hierarchical recursive encoder-decoder framework with two enhanced self-attention encoders to capture the semantic signal and emotional signal, respectively, which are then fused in the decoder to produce the response. In general, we consider the dynamic and potential information of emotion to generate the response in multi-turn dialogues in the field of both daily conversation and psychological counseling. Our experimental results on a daily Chinese conversation dataset and a psychological counseling dataset show that ECCM outperforms the state-of-the-art baselines in terms of Perplexity, Distinct-1, Distinct-2, and manual evaluation. In addition, we find that ECCM performs well for input contexts with different lengths.