Perspective-taking and Pragmatics for Generating Empathetic Responses Focused on Emotion Causes

Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 2227–2240 November 7–11, 2021. c⃝2021 Association for Computational Linguistics 2227 Perspective-taking and Pragmatics for Generating Empathetic Responses Focused on Emotion Causes Hyunwoo Kim Byeongchang Kim Gunhee Kim Department of Computer Science and Engineering Seoul National University, Seoul, Korea {hyunw.kim, byeongchang.kim}@vl.snu.ac.kr gunhee@snu.ac.kr https://vl.snu.ac.kr/projects/focused-empathy Abstract Empathy is a complex cognitive ability based on the reasoning of others’ affective states. In order to better understand others and ex- press stronger empathy in dialogues, we argue that two issues must be tackled at the same time: (i) identifying which word is the cause for the other’s emotion from his or her utter- ance and (ii) reflecting those specific words in the response generation. However, previ- ous approaches for recognizing emotion cause words in text require sub-utterance level anno- tations, which can be demanding. Taking in- spiration from social cognition, we leverage a generative estimator to infer emotion cause words from utterances with no word-level la- bel. Also, we introduce a novel method based on pragmatics to make dialogue models focus on targeted words in the input during gener- ation. Our method is applicable to any dia- logue models with no additional training on the fly. We show our approach improves mul- tiple best performing dialogue agents on gen- erating more focused empathetic responses in terms of both automatic and human evaluation. 1 Introduction Empathy is one of the hallmarks of social cogni- tion. It is an intricate cognitive ability that requires high-level reasoning on other’s affective states. The intensity of expressed empathy varies depending on the depth of reasoning. According to Sharma et al. (2020), weak empathy is accompanied by generic expressions such as “Are you OK?” or “It’s just ter- rible, isn’t it?”, while stronger empathy reflects the other’s specific situation: “How is your headache, any better?” or “You must be worried about the job interview”. In order to respond with stronger empathy, two issues must be tackled: reasoning (i) where to focus on the interlocutor’s utterance (for the reason behind the emotion) and (ii) how to generate utterances that focus on such words. Firstly, which words should we focus on when empathizing with others? As empathy relates to other’s emotional states, the reasons behind emo- tions (emotion cause) should be identified. Imagine you are told “I got a gift from a friend last vaca- tion!” with a joyful face. The likely words that can be the causes of his/her happiness are “gift” and “friend”. On the other hand, “vacation” has less to do with the emotion. If you respond “How was your vacation?”, the interlocutor may think you are not interested; rather, it is better to say “Wow, what was the gift?” or “Your friend must really like you.” by focusing on the emotion cause words. We humans do not rely on word-level supervi- sion for such affective reasoning. Instead, we put ourselves in the other’s shoes and simulate what it would be like. Perspective-taking is this act of …

Content truncated to 500 words