EMNLP Findings2021
A Discourse-Aware Graph Neural Network for Emotion Recognition in Multi-Party Conversation
Abstract
Emotion recognition in multi-party conversation (ERMC) is becoming increasingly popular as an emerging research topic in natural language processing. Prior research focuses on exploring sequential information but ignores the discourse structures of conversations. In this paper, we investigate the importance of discourse structures in handling informative contextual cues and speaker-specific features for ERMC. To this end, we propose a discourse-aware graph neural network (ERMC-DisGCN) for ERMC. In particular, we design a relational convolution to lever the self-speaker dependency of interlocutors to propagate contextual information. Furthermore, we exploit a gated convolution to select more informative cues for ERMC from dependent utterances. The experimental results show our method outperforms multiple baselines, illustrating that discourse structures are of great value to ERMC.
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.
7 top-tier papers have cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
- BIG-FUSION: Brain-Inspired Global-Local Context Fusion Framework for Multimodal Emotion Recognition in Conversations cites DualGATs: Dual Graph Attention Networks for Emotion Recognition in Conversations
- DualGATs: Dual Graph Attention Networks for Emotion Recognition in Conversations cites Multi-turn Response Selection using Dialogue Dependency Relations
- DualGATs: Dual Graph Attention Networks for Emotion Recognition in Conversations cites DialogXL: All-in-One XLNet for Multi-Party Conversation Emotion Recognition
- Bridging Visual Affective Gap: Borrowing Textual Knowledge by Learning from Noisy Image-Text Pairs cites Tackling Modality Heterogeneity with Multi-View Calibration Network for Multimodal Sentiment Detection
Cited by top-tier papers7
- UniMSE: Towards Unified Multimodal Sentiment Analysis and Emotion RecognitionGuimin Hu, Ting-En Lin, Yi Zhao, Guangming Lu et al.EMNLP 2022 · 206 citations
- DualGATs: Dual Graph Attention Networks for Emotion Recognition in ConversationsDuzhen Zhang, Feilong Chen, Xiuyi ChenACL 2023 · 54 citations
- Tackling Modality Heterogeneity with Multi-View Calibration Network for Multimodal Sentiment DetectionYiwei Wei, Shaozu Yuan, Ruosong Yang, Lei Shen et al.ACL 2023 · 42 citations
- BIG-FUSION: Brain-Inspired Global-Local Context Fusion Framework for Multimodal Emotion Recognition in ConversationsYusong Wang, Xuanye Fang, Huifeng Yin, Dongyuan Li et al.AAAI 2025 · 11 citations
- Bridging Visual Affective Gap: Borrowing Textual Knowledge by Learning from Noisy Image-Text PairsDaiqing Wu, Dongbao Yang, Yu Zhou, Can MaACM MM 2024 · 6 citations
Builds on3
- DialogXL: All-in-One XLNet for Multi-Party Conversation Emotion RecognitionWeizhou Shen, Junqing Chen, Xiaojun Quan, Zhixian XieAAAI 2021 · 251 citations
- Multi-turn Response Selection using Dialogue Dependency RelationsQi Jia, Yizhu Liu, Siyu Ren, Kenny Q. Zhu et al.EMNLP 2020 · 31 citations
- Syntax-Aware Opinion Role Labeling with Dependency Graph Convolutional NetworksBo Zhang, Yue Zhang, Rui Wang, Zhenghua Li et al.ACL 2020 · 30 citations
Related papers
- Relation-aware Graph Attention Networks with Relational Position Encodings for Emotion Recognition in ConversationsTaichi Ishiwatari, Yuki Yasuda, Taro Miyazaki, Jun GotoEMNLP 2020 · 201 citations
- MMGCN: Multimodal Fusion via Deep Graph Convolution Network for Emotion Recognition in ConversationJingwen Hu, Yuchen Liu, Jinming Zhao, Qin JinACL 2021
- Multivariate, Multi-Frequency and Multimodal: Rethinking Graph Neural Networks for Emotion Recognition in ConversationFeiyu Chen, Jie Shao, Shuyuan Zhu, Heng Tao ShenCVPR 2023
- SKIER: A Symbolic Knowledge Integrated Model for Conversational Emotion RecognitionWei Li, Luyao Zhu, Rui Mao, Erik CambriaAAAI 2023 · 85 citations
- Dynamic Interactive Bimodal Hypergraph Networks for Emotion Recognition in ConversationsXuping Chen, Wuzhen ShiAAAI 2025 · 3 citations
