CASE: Aligning Coarse-to-Fine Cognition and Affection for Empathetic Response Generation

Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics Volume 1: Long Papers, pages 8223–8237 July 9-14, 2023 ©2023 Association for Computational Linguistics CASE: Aligning Coarse-to-Fine Cognition and Affection for Empathetic Response Generation Jinfeng Zhou1,2∗ † Chujie Zheng1† Bo Wang2‡ Zheng Zhang1 Minlie Huang1 1The CoAI Group, DCST, Institute for Artificial Intelligence, State Key Lab of Intelligent Technology and Systems, 1Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing 100084, China 2College of Intelligence and Computing, Tianjin University, Tianjin, China {jfzhou.mail, chujiezhengchn, zhangz.goal}@gmail.com, bo_wang@tju.edu.cn, aihuang@tsinghua.edu.cn Abstract Empathetic conversation is psychologically supposed to be the result of conscious align- ment and interaction between the cognition and affection of empathy. However, existing empa- thetic dialogue models usually consider only the affective aspect or treat cognition and affec- tion in isolation, which limits the capability of empathetic response generation. In this work, we propose the CASE model for empathetic dialogue generation. It first builds upon a com- monsense cognition graph and an emotional concept graph and then aligns the user’s cogni- tion and affection at both the coarse-grained and fine-grained levels. Through automatic and manual evaluation, we demonstrate that CASE outperforms state-of-the-art baselines of empathetic dialogues and can generate more empathetic and informative responses.1 1 Introduction Human empathetic conversations allow both parties to understand each other’s experiences and feelings (Keskin, 2014), which is crucial for establishing seamless relationships (Zech and Rimé, 2005) and is also integral to building a trustful conversational AI (Huang et al., 2020; Wang et al., 2021). In social psychology, empathy consists of two aspects: cognition and affection (Davis, 1983). The cognitive aspect corresponding to the understand- ing of the user’s situation and experiences (Cuff et al., 2016). The affective aspect requires the com- prehension of the user’s emotional state and his/her potential emotional reaction (Elliott et al., 2018). Although existing work of empathetic dialogue in- volves both aspects of empathy, there are still is- sues that need to be addressed. First, most work (Rashkin et al., 2019; Lin et al., 2019; Majumder ∗Work done during internship at the CoAI Group. †Equal contribution. ‡Corresponding author. 1The project repository is available at https://github. com/jfzhouyoo/CASE Context-1a: My family and I are going on vacation in a few weeks. We rented a largo beachfront condo and I can not wait! Context-1b: We went to sunbathe by the sea about a week ago and it rained several days while we were there. To go to the beach Excited Disappointed To give up To try harder Frustrated Hopeful Context-2: I have been passively job hunting for a few months now. I haven't had any luck yet and I am starting to feel like I never will. Response-1a: Oh, I love the beach!! which beach are you going to go to? Response-1b: I hate when that happens! Especially when you have been waiting for the beach! Response-2a: Please do not ever give up. I would definitely work harder to find a job by networking with friends. Response-2b: Keep trying hard, …

Content truncated to 500 words