Samsung Research China-Beijing at SemEval-2024 Task 3: A multi-stage framework for Emotion-Cause Pair Extraction in Conversations
Not on the map. Why?
Abstract (arXiv)
In human-computer interaction, it is crucial for agents to respond to human by understanding their emotions. Unraveling the causes of emotions is more challenging. A new task named Multimodal Emotion-Cause Pair Extraction in Conversations is responsible for recognizing emotion and identifying causal expressions. In this study, we propose a multi-stage framework to generate emotion and extract the emotion causal pairs given the target emotion. In the first stage, Llama-2-based InstructERC is utilized to extract the emotion category of each utterance in a conversation. After emotion recognition, a two-stream attention model is employed to extract the emotion causal pairs given the target emotion for subtask 2 while MuTEC is employed to extract causal span for subtask 1. Our approach achieved first place for both of the two subtasks in the competition.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 34 of its 56 references that are in the map. First posted on arXiv 25 Apr 2024.
Builds on
34 of 56 references.
References · 34
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
- 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
- 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,372
- 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
- 2023Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understandingcited by 1,471
- 2016Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networkscited by 903
- 2019SpanBERT: Improving Pre-training by Representing and Predicting Spanscited by 834
- 2017DailyDialog: A Manually Labelled Multi-turn Dialogue Datasetcited by 652
- 2018MELD: A Multimodal Multi-Party Dataset for Emotion Recognition in Conversationscited by 643
- 2016Deep Biaffine Attention for Neural Dependency Parsingcited by 334
- 2018DialogueRNN: An Attentive RNN for Emotion Detection in Conversationscited by 218
- 2019DialogueGCN: A Graph Convolutional Neural Network for Emotion Recognition in Conversationcited by 186
22 more
- 2018MobileFaceNets: Efficient CNNs for Accurate Real-Time Face Verification on Mobile Devicescited by 182
- 2019Dice Loss for Data-imbalanced NLP Taskscited by 182
- 2020COSMIC: COmmonSense knowledge for eMotion Identification in Conversationscited by 136
- 2017Emotion Detection on TV Show Transcripts with Sequence-based Convolutional Neural Networkscited by 102
- 2021Directed Acyclic Graph Network for Conversational Emotion Recognitioncited by 97
- 2019Knowledge-Enriched Transformer for Emotion Detection in Textual Conversationscited by 92
- 2019Emotion-Cause Pair Extraction: A New Task to Emotion Analysis in Textscited by 83
- 2020DialogXL: All-in-One XLNet for Multi-Party Conversation Emotion Recognitioncited by 79
- 2020Recognizing Emotion Cause in Conversationscited by 66
- 2021EmoBERTa: Speaker-Aware Emotion Recognition in Conversation with RoBERTacited by 60
- 2021Topic-Driven and Knowledge-Aware Transformer for Dialogue Emotion Detectioncited by 56
- 2022M2FNet: Multi-modal Fusion Network for Emotion Recognition in Conversationcited by 47
- 2021Multimodal Emotion-Cause Pair Extraction in Conversationscited by 31
- 2022Supervised Prototypical Contrastive Learning for Emotion Recognition in Conversationcited by 31
- 2022GraphCFC: A Directed Graph Based Cross-Modal Feature Complementation Approach for Multimodal Conversational Emotion Recognitioncited by 20
- 2023Supervised Adversarial Contrastive Learning for Emotion Recognition in Conversationscited by 19
- 2022Knowledge-Bridged Causal Interaction Network for Causal Emotion Entailmentcited by 16
- 2022Neutral Utterances are Also Causes: Enhancing Conversational Causal Emotion Entailment with Social Commonsense Knowledgecited by 13
- 2020Multi-Task Learning with Auxiliary Speaker Identification for Conversational Emotion Recognitioncited by 12
- 2022TSAM: A Two-Stream Attention Model for Causal Emotion Entailmentcited by 6
- 2023Hierarchical Dialogue Understanding with Special Tokens and Turn-level Attentioncited by 6
- 2022Multi-Task Learning Framework for Extracting Emotion Cause Span and Entailment in Conversationscited by 3
Built on by
Citing papers per year: 2024: 1; 2025: 1.
2 papers.