Using Extracted Emotion Cause to Improve Content-Relevance for Empathetic Conversation Generation

Using Extracted Emotion Cause to Improve Content-Relevance for Empathetic Conversation Generation Minghui Zou∗, Rui Pan∗, Sai Zhang†, Xiaowang Zhang College of Intelligence and Computing, Tianjin University, Tianjin, China zhang sai@tju.edu.cn Abstract Empathetic conversation generation intends to endow the open-domain conversation model with the capability for understanding, interpreting, and expressing emotion. Humans express not only their emotional state but also the stimulus that caused the emotion, i.e., emotion cause, dur- ing a conversation. Most existing approaches focus on emotion modeling, emotion recogni- tion and prediction, and emotion fusion generation, ignoring the critical aspect of the emotion cause, which results in generating responses with irrelevant content. Emotion cause can help the model understand the user’s emotion and make the generated responses more content-relevant. However, using the emotion cause to enhance empathetic conversation generation is challenging. Firstly, the model needs to accurately identify the emotion cause without large-scale labeled data. Second, the model needs to effectively integrate the emotion cause into the generation process. To this end, we present an emotion cause extractor using a semi-supervised training method and an empathetic conversation generator using a biased self-attention mechanism to overcome these two issues. Experimental results indicate that our proposed emotion cause extractor improves recall scores markedly compared to the baselines, and the proposed empathetic conversation generator has superior performance and improves the content-relevance of generated responses. 1 Introduction Open-domain conversation generation has made remarkable progress over recent years, relying on deep learning and neural networks (Serban et al., 2016; Wolf et al., 2019; Zhou et al., 2020; Huang et al., 2020). However, previous works primarily centre around improving the linguistic quality of the gen- erated responses, such as grammatical correctness, content variety, and topic relevance, neglecting the important factor of emotion (Zhou et al., 2018). The information conveyed by humans during communi- cation contains not only syntactic and semantic information but also emotional information. Emotion is one of the essential cognitive behaviors in humans, and artificial intelligence has the objective of enabling machines to mimic human intelligent behaviors. As an important research branch of AI, one of the long- term goals of dialogue systems is to enable machines to perceive, comprehend and express emotions. In addition, studies (Martinovski and Traum, 2003; Prendinger and Ishizuka, 2005; Prendinger et al., 2005) have shown that introducing emotional information into conversation systems can improve user engagement and satisfaction, make human-computer conversation more natural, and reduce the number of conversation terminations. As a new research hotspot for the NLP community, most existing approaches on empathetic con- versation generation focus on identifying the emotion category of the input sequence and generating a response based on the predicted emotion label. Song et al. (2019) introduce an external emotion lexicon into the generation module to achieve explicit and implicit emotion expression. Li et al. (2020) create a coarse-grained and fine-grained emotion representation for the input sequence by using an emotion classifier to identify the input sequence’s emotion category and an external emotion lexicon to identify *These authors contributed equally to this …

Content truncated to 500 words