FATRER：面向精准鲁棒对话情绪识别的全注意力主题正则化器
FATRER: Full-Attention Topic Regularizer for Accurate and Robust Conversational Emotion Recognition
AI总结：
针对对话情绪识别中现有模型忽略对抗攻击下鲁棒性的问题，提出带全注意力主题正则化器的情绪识别模型，通过联合主题建模和无先验注意力概率近似，兼顾准确率与对抗鲁棒性，性能优于现有最优模型。
摘要：
本文聚焦于对话话语中引发的对话者情绪理解问题。该领域以往研究主要关注提升情绪预测的准确率，却忽略了局部上下文遭对抗攻击破坏时的模型鲁棒性。为在保证准确率的同时维持鲁棒性，我们提出一种由全注意力主题正则化器增强的情绪识别模型，该模型在对对话中的局部上下文建模时，能引入与情绪相关的全局视角。我们引入联合主题建模策略，从表征和损失两个层面实现正则化。为避免过度正则化，我们摒弃了传统主题建模中存在的先验分布约束，完全基于注意力对齐进行概率近似。实验表明，我们的模型相比当前最优（SOTA）模型取得了更优的结果，并且在三类对抗攻击下展现出令人信服的鲁棒性。
英文摘要：
This paper concentrates on the understanding of interlocutors' emotions evoked in conversational utterances. Previous studies in this literature mainly focus on more accurate emotional predictions, while ignoring model robustness when the local context is corrupted by adversarial attacks. To maintain robustness while ensuring accuracy, we propose an emotion recognizer augmented by a full-attention topic regularizer, which enables an emotion-related global view when modeling the local context in a conversation. A joint topic modeling strategy is introduced to implement regularization from both representation and loss perspectives. To avoid over-regularization, we drop the constraints on prior distributions that exist in traditional topic modeling and perform probabilistic approximations based entirely on attention alignment. Experiments show that our models obtain more favorable results than state-of-the-art models, and gain convincing robustness under three types of adversarial attacks.
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。
