EMNLP Findings2022
Empathetic and Emotionally Positive Conversation Systems with an Emotion-specific Query-Response Memory
Zhiliang Tian, Yinliang Wang, Yiping Song, Chi Zhang, Dongkyu Lee, Yingxiu Zhao, Dongsheng Li, Nevin L. Zhang
Abstract
Emotional conversation systems generate responses for the input queries considering the speaker's emotions in a conversation. Existing emotional conversation systems output emotional responses according to either a given emotion or the user's emotion reflected in the input queries. Following a given emotion may lead to an emotional drift between the given emotion and the conversation state, and following only the user's emotion may aggravate the user's negative feelings if users suffer from a negative mood. In this paper, we propose to generate empathetic responses catering to the user's emotions while leading the conversation to be emotionally positive. Particularly, by abstracting the conversation corpus, we extract and store the different responding strategies for different users' emotions and conversational topics into a memory. We encourage positive emotions in conversation via a sentiment evaluator. We model the memory outputs with a Gaussian mixture distribution and sample a final responding strategy from the distribution. The strategy acts as a condition to a transformer model to generate responses. The experiments verify our model surpasses the baseline methods in appropriateness, diversity, and generating emotionally positive responses.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
Lineage
Builds on10
- Plug and Play Language Models: A Simple Approach to Controlled Text GenerationSumanth Dathathri, Andrea Madotto, Janice Lan, Jane Hung et al.ICLR 2020 · 1,166 citations
- Deep Clustering by Gaussian Mixture Variational Autoencoders With Graph EmbeddingLinxiao Yang, Ngai-Man Cheung, Jiaying Li, Jun FangICCV 2019 · 149 citations
- Knowledge Bridging for Empathetic Dialogue GenerationQintong Li, Piji Li, Zhaochun Ren, Pengjie Ren et al.AAAI 2022 · 128 citations
- Towards Persona-Based Empathetic Conversational ModelsPeixiang Zhong, Chen Zhang, Hao Wang, Yong Liu et al.EMNLP 2020 · 112 citations
- Improving Empathetic Response Generation by Recognizing Emotion Cause in ConversationsJun Gao, Yuhan Liu, Haolin Deng, Wei Wang et al.EMNLP Findings 2021 · 87 citations
Related papers
- Facilitating Multi-turn Emotional Support Conversation with Positive Emotion Elicitation: A Reinforcement Learning ApproachJinfeng Zhou, Zhuang Chen, Bo Wang, Minlie HuangACL 2023 · 17 citations
- Emotion Trajectory-aware Retrieval for Markov-driven Emotion Anticipation in LLM-based Emotional Support ConversationHongyan Wu, Zhiliang Tian, Zhen Huang, Tengyue Hu et al.ACL Findings 2026
- An Iterative Associative Memory Model for Empathetic Response GenerationZhou Yang, Zhaochun Ren, Yufeng Wang, Haizhou Sun et al.ACL 2024
- Constructing Emotional Consensus and Utilizing Unpaired Data for Empathetic Dialogue GenerationLei Shen, Jinchao Zhang, Jiao Ou, Xiaofang Zhao et al.EMNLP Findings 2021 · 18 citations
- More the Merrier: Towards Multi-Emotion and Intensity Controllable Response GenerationMauajama Firdaus, Hardik Chauhan, Asif Ekbal, Pushpak BhattacharyyaAAAI 2021 · 13 citations
