Locate and Explain: Joint Multimodal Emotion Cause Extraction and Summarization in Conversation
Jikun Wan, Chen Gong, Guohong Fu
摘要
Multimodal emotion cause analysis in conversation aims to identify the causes of emotions by leveraging multimodal information. Existing studies mainly formulate this problem as either utterance-level emotion cause extraction, which provides clear cause localization but limited explanation, or multimodal emotion cause generation, which offers fine-grained explanations but lacks explicit traceability to source utterances. Moreover, existing datasets rely heavily on human judgment and lack well-defined structured theoretical guidance, leading to subjective and inconsistent annotations. To address these issues, we introduce joint Multimodal Emotion Cause Extraction and Summarization in conversation (MECES), a new task that simultaneously extracts emotion cause utterances and generates cause summaries, enabling both precise localization and interpretable explanations of emotion cause. We further construct a MECES dataset guided by the Activating events-Beliefs-Consequences theory from psychology. This dataset consists of 5,787 emotion utterances annotated with causes, comprising 12,231 emotion-cause pairs and 6,040 cause summaries. We also propose an effective endto-end joint learning approach for MECES task, establishing strong benchmark results for this newly introduced task and dataset. * Corresponding author. ( U1,U2 , "Chuan Bai handed Guang Shi a gift, and Guang Shi didn't expect to receive one too.") Guang Shi: "I got a gift too!" Guang Shi: "Thank you, teacher!" Guang Shi: "Teacher, this gift of yours is really practical..." U1 U2 U3 U4 U5 Chuan Bai: "Here, this is from the teacher for you." Chuan Bai: "Achieving this rank is just the first step you've taken. learning Go is endless. Go back and read it carefully!" Neutral Surprise Happy Sad Neutral Why does Guang Shi feel Surprised,Happy and Sad in this dialog? ( U4 , "Guang Shi discovered the gift his teacher gave him was a Go book, he didn't expect the teacher's gift would be for him to study again") ( U1,U2 , "Chuan Bai handed Guang Shi a gift, and Guang Shi didn't expect to receive one too.")
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了每一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
它引用的顶会 Paper7
- BERTScore: Evaluating Text Generation with BERTTianyi Zhang, Varsha Kishore, Felix Wu, Kilian Q. Weinberger 等ICLR 2020 · 被引用 8,443 次
- M3ED: Multi-modal Multi-scene Multi-label Emotional Dialogue DatabaseJinming Zhao, Tenggan Zhang, Jingwen Hu, Yuchen Liu 等ACL 2022 · 被引用 88 次
- MSE-Adapter: A Lightweight Plugin Endowing LLMs with the Capability to Perform Multimodal Sentiment Analysis and Emotion RecognitionYang Yang, Xunde Dong, Yupeng QiangAAAI 2025 · 被引用 19 次
- Observe before Generate: Emotion-Cause aware Video Caption for Multimodal Emotion Cause Generation in ConversationsFanfan Wang, Heqing Ma, Xiangqing Shen, Jianfei Yu 等ACM MM 2024 · 被引用 6 次
- Emotion across Modalities and Cultures: Multilingual Multimodal Emotion-Cause Analysis with Memory-inspired FrameworkDan Wu, Xincheng Ju, Dong Zhang, Shoushan Li 等ACM MM 2025 · 被引用 2 次
相关 Paper
- ECFCON: Emotion Consequence Forecasting in ConversationsXincheng Ju, Dong Zhang, Suyang Zhu, Junhui Li 等ACM MM 2024 · 被引用 1 次
- From Coarse to Fine: A Distillation Method for Fine-Grained Emotion-Causal Span Pair Extraction in ConversationXinhao Chen, Chong Yang, Changzhi Sun, Man Lan 等AAAI 2024 · 被引用 7 次
- Why Do Emotions Change? Appraisal-Guided Reasoning for Emotion-Cause Triplet Extraction in ConversationsQiao Liang, Ying Shen, Yao Liu, Tiantian Chen 等ACL 2026
- End-to-End Emotion-Cause Pair Extraction based on Sliding Window Multi-Label LearningZixiang Ding, Rui Xia, Jianfei YuEMNLP 2020 · 被引用 85 次
- ECC: An Emotion-Cause Conversation Dataset for Empathy ResponseYuanyuan He, Yongsen Pan, Wei Li, Jiali You 等EMNLP 2025
