提出LSDGNN与改进课程学习，提升对话情感识别准确率
Long-Short Distance Graph Neural Networks and Improved Curriculum Learning for Emotion Recognition in Conversation
- 构建长短距离图网络分别捕捉远近话语特征
- 在IEMOCAP和MELD上达到87.6%和83.4%准确率
- 适合需要精准情感分析的对话系统研发
对话情感识别（ERC）是一项实际且具有挑战性的任务。本文提出一种新颖的多模态方法——长-短距离图神经网络（LSDGNN）。基于有向无环图（DAG），构建长距离和短距离图神经网络，分别提取远距离与邻近话语的多模态特征。为确保两类特征表示差异最大化，同时促进模块间相互作用，引入差分正则化器，并加入双向仿射模块以增强特征交互。此外，提出改进课程学习（ICL）以应对数据不平衡问题。通过计算不同情绪间的相似性，设计“加权情感转移”度量指标，构建难度评估器，实现从易到难的渐进式训练。在IEMOCAP和MELD数据集上的实验结果表明，该模型优于现有基准。
原文摘要 · Abstract (English)
Emotion Recognition in Conversation (ERC) is a practical and challenging task. This paper proposes a novel multimodal approach, the Long-Short Distance Graph Neural Network (LSDGNN). Based on the Directed Acyclic Graph (DAG), it constructs a long-distance graph neural network and a short-distance graph neural network to obtain multimodal features of distant and nearby utterances, respectively. To ensure that long- and short-distance features are as distinct as possible in representation while enabling mutual influence between the two modules, we employ a Differential Regularizer and incorporate a BiAffine Module to facilitate feature interaction. In addition, we propose an Improved Curriculum Learning (ICL) to address the challenge of data imbalance. By computing the similarity between different emotions to emphasize the shifts in similar emotions, we design a "weighted emotional shift" metric and develop a difficulty measurer, enabling a training process that prioritizes learning easy samples before harder ones. Experimental results on the IEMOCAP and MELD datasets demonstrate that our model outperforms existing benchmarks.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。