Samsung Research China-Beijing at SemEval-2024 Task 3: A multi-stage framework for Emotion-Cause Pair Extraction in Conversations

TL;DR

This paper presents a multi-stage framework for extracting emotion and their causes in conversations, combining emotion recognition and causal span extraction, achieving top results in SemEval-2024 Task 3.

Contribution

It introduces a novel multi-stage approach utilizing Llama-2, attention models, and MuTEC for emotion-cause pair extraction in conversations, outperforming existing methods.

Findings

Achieved first place in both subtasks of SemEval-2024 Task 3.

Effective combination of emotion recognition and causal span extraction.

Demonstrated the effectiveness of multi-stage modeling in emotion-cause analysis.

Abstract

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.