通过对话特征显式区分发言轮次，提升多轮情感识别效果
TED: Turn Emphasis with Dialogue Feature Attention for Emotion Recognition in Conversation
- 在注意力机制中引入发言轮次与说话人信息作为优先级特征
- 在IEMOCAP数据集上实现当前最佳性能，尤其适用于长对话场景
- 无需特殊标记即可增强模型对多轮对话结构的理解，适合对话系统研究者
多轮对话中的情感识别（ERC）近年来受到广泛关注，现有方法依赖预训练模型对多轮输入的隐式区分，通常通过插入特殊标记来实现。本文提出一种基于优先级的注意力机制——对话特征强调（TED），通过将发言轮次位置和说话人信息作为对话特征显式融入注意力计算，以明确区分各发言轮次。该方法对基于轮次的向量进行多头自注意力，并利用对话特征动态调整注意力分数。在四个典型基准数据集上的实验表明，TED在所有数据集上均表现优异，在发言轮次较多的IEMOCAP数据集上达到当前最优性能。
原文摘要 · Abstract (English)
Emotion recognition in conversation (ERC) has been attracting attention by methods for modeling multi-turn contexts. The multi-turn input to a pretraining model implicitly assumes that the current turn and other turns are distinguished during the training process by inserting special tokens into the input sequence. This paper proposes a priority-based attention method to distinguish each turn explicitly by adding dialogue features into the attention mechanism, called Turn Emphasis with Dialogue (TED). It has a priority for each turn according to turn position and speaker information as dialogue features. It takes multi-head self-attention between turn-based vectors for multi-turn input and adjusts attention scores with the dialogue features. We evaluate TED on four typical benchmarks. The experimental results demonstrate that TED has high overall performance in all datasets and achieves state-of-the-art performance on IEMOCAP with numerous turns.
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。