NUS-Emo at SemEval-2024 Task 3：面向对话中多模态情感-原因分析的指令微调LLM
NUS-Emo at SemEval-2024 Task 3: Instruction-Tuning LLM for Multimodal Emotion-Cause Analysis in Conversations
AI总结：
本文针对SemEval-2024多模态情感-原因对提取任务，提出基于LLM的情感-原因感知指令微调方法，结合ERC与ECPE双组件系统，实现34.71%加权F1分数并获排行榜第二名。
摘要：
本文描述了我们为SemEval-2024 Task 3：对话中多模态情感-原因分析开发的系统架构。我们的项目针对子任务2的挑战，致力于带情感类别的多模态情感-原因对提取（MECPE-Cat），并构建了一个针对该任务独特挑战量身定制的双组件系统。我们将任务分为两个子任务：对话中的情感识别（ERC）和情感-原因对提取（ECPE）。为解决这些子任务，我们利用了大型语言模型（LLMs）的能力，它们在各种自然语言处理任务和领域中始终展现出最先进的性能。最重要的是，我们设计了一种面向LLMs的情感-原因感知指令微调方法，以增强对情感及其对应因果依据的感知。我们的方法使我们能够熟练应对MECPE-Cat的复杂性，实现了该任务34.71%的加权平均F1分数，并在排行榜上获得第2名。用于复现我们实验的代码和元数据均已公开。
英文摘要：
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 dual-component 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 instruction-tuning 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 2nd rank on the leaderboard. The code and metadata to reproduce our experiments are all made publicly available.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
