MIME: MIMicking Emotions for Empathetic Response Generation

Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing, pages 8968–8979, November 16–20, 2020. c⃝2020 Association for Computational Linguistics 8968 MIME: MIMicking Emotions for Empathetic Response Generation Navonil Majumder†, Pengfei Hong†, Shanshan Peng†∗, Jiankun Lu†∗, Deepanway Ghosal†, Alexander Gelbukh⋄, Rada Mihalcea△, Soujanya Poria† † Singapore University of Technology and Design, Singapore ⋄ CIC, Instituto Polit´ecnico Nacional, Mexico △ University of Michigan, USA {navonil majumder, sporia}@sutd.edu.sg, {shanshan peng, jiankun liu}@mymail.sutd.edu.sg, {pengfei hong, deepanway ghosal}@mymail.sutd.edu.sg, gelbukh@cic.ipn.mx, mihalcea@umich.edu Abstract Current approaches to empathetic response generation view the set of emotions expressed in the input text as a flat structure, where all the emotions are treated uniformly. We argue that empathetic responses often mimic the emotion of the user to a varying degree, depending on its positivity or negativity and content. We show that the consideration of these polarity- based emotion clusters and emotional mimicry results in improved empathy and contextual relevance of the response as compared to the state-of-the-art. Also, we introduce stochas- ticity into the emotion mixture that yields emotionally more varied empathetic responses than the previous work. We demonstrate the importance of these factors to empathetic re- sponse generation using both automatic- and human-based evaluations. The implementa- tion of MIME is publicly available at https: //github.com/declare-lab/MIME. 1 Introduction Empathy is a fundamental human trait that reflects our ability to understand and reflect the thoughts and feelings of the people we interact with. In the social sciences, research on empathy has evolved into an entire field of study, addressing the so- cial underpinning of empathy (Singer and Lamm, 2009), the cognitive and emotion aspects of empa- thy (Smith, 2006), and its connection to personal and demographic traits (Dymond, 1950; Eisenberg et al., 2014; Krebs, 1975). The study of empathy has found a wide range of applications in health- care, including psychotherapy (Bohart and Green- berg, 1997) or more broadly as a mechanism to improve the quality of care (Mercer and Reynolds, 2002). Computational models of empathy have been proposed only in recent years, partly because of ∗ signifies equal contribution User I am so excited because I am finally going to visit my parents next month! I did not see them for 3 years. Joyful Empathetic Response (GOLD) 3 years is a long time. How come? Figure 1: An instance where a positive context is re- sponded with ambivalence. the complexity of this behavior which makes it dif- ficult to emulate with computational approaches. In natural language processing, the methods pro- posed to date address the tasks of understand- ing expressions of empathy in newswire (Buechel et al., 2018), counseling conversations (P´erez- Rosas et al., 2017), or generating empathy in dia- logue (Shen et al., 2020; Lin et al., 2019). Work has also been done on the construction of empa- thy lexicons (Sedoc et al., 2020) or large empathy dialogue datasets (Rashkin et al., 2019). In this paper, we address the task of generat- ing empathetic responses that mimic the emotion of the speaker while accounting for their affective …

Content truncated to 500 words