NUS-Emo at SemEval-2024 Task 3: Instruction-Tuning LLM for Multimodal Emotion-Cause Analysis in Conversations
Meng Fan Luo, Han Zhang, Shengqiong Wu, Bobo Li, Hong Wei Han, Hao Fei · 2024
This paper describes the architecture of our system developed for Task 3 of SemEval-2024: Multimodal Emotion-Cause Analysis in Conversations.Our project targets the challenges of subtask 2, dedicated to Multimodal Emotion-Cause Pair Extraction with Emotion Category (MECPE-Cat), and constructs a dualcomponent system tailored to the unique challenges of this task.We divide the task into two subtasks: emotion recognition in conversation (ERC) and emotion-cause pair extraction (ECPE).To address these subtasks, we capitalize on the abilities of Large Language Models (LLMs), which have consistently demonstrated state-of-the-art performance across various natural language processing tasks and domains.Most importantly, we design an approach of emotion-cause-aware instructiontuning for LLMs, to enhance the perception of the emotions with their corresponding causal rationales.Our method enables us to adeptly navigate the complexities of MECPE-Cat, achieving a weighted average 34.71%F1 score of the task, and securing the 2 nd rank on the leaderboard.1 The code and metadata to reproduce our experiments are all made publicly available.2