面向对话情感识别的监督对抗对比学习
Supervised Adversarial Contrastive Learning for Emotion Recognition in Conversations
AI总结：
本文提出监督对抗对比学习框架SACL及上下文对抗训练策略CAT，并构建SACL-LSTM模型，在三个对话情感识别数据集上取得最先进性能。
摘要：
提取泛化且鲁棒的表示是对话情感识别（ERC）中的一个主要挑战。为了解决这一问题，我们提出了一种监督对抗对比学习（SACL）框架，以监督方式学习类别分散的结构化表示。SACL 应用对比感知的对抗训练来生成最坏情况样本，并使用联合类别分散对比学习来提取结构化表示。它能够有效利用标签级特征一致性，并保留细粒度的类内特征。为了避免对抗扰动对上下文依赖数据的负面影响，我们设计了一种上下文对抗训练（CAT）策略，以从上下文中学习更多样化的特征，并增强模型的上下文鲁棒性。在带有 CAT 的框架下，我们开发了一种基于序列的 SACL-LSTM，用于为 ERC 学习标签一致且上下文鲁棒的特征。在三个数据集上的实验表明，SACL-LSTM 在 ERC 上取得了最先进的性能。扩展实验证明了 SACL 和 CAT 的有效性。
英文摘要：
Extracting generalized and robust representations is a major challenge in emotion recognition in conversations (ERC). To address this, we propose a supervised adversarial contrastive learning (SACL) framework for learning class-spread structured representations in a supervised manner. SACL applies contrast-aware adversarial training to generate worst-case samples and uses joint class-spread contrastive learning to extract structured representations. It can effectively utilize label-level feature consistency and retain fine-grained intra-class features. To avoid the negative impact of adversarial perturbations on context-dependent data, we design a contextual adversarial training (CAT) strategy to learn more diverse features from context and enhance the model's context robustness. Under the framework with CAT, we develop a sequence-based SACL-LSTM to learn label-consistent and context-robust features for ERC. Experiments on three datasets show that SACL-LSTM achieves state-of-the-art performance on ERC. Extended experiments prove the effectiveness of SACL and CAT.
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。
