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.

翻译：对话情感识别（ERC）通过建模多轮次上下文的方法持续受到关注。现有方法通常将多轮次输入馈送至预训练模型，通过在输入序列中插入特殊标记，隐式地假设当前轮次与其他轮次在训练过程中得以区分。本文提出一种基于优先级的注意力方法，通过将对话特征融入注意力机制来显式区分各轮次，称为基于对话的轮次强调（TED）。该方法依据轮次位置和说话者信息等对话特征为每个轮次分配优先级。它首先在多轮次输入生成的轮次向量间进行多头自注意力计算，随后利用对话特征调整注意力得分。我们在四个典型基准数据集上评估TED。实验结果表明，TED在所有数据集上均展现出优异的整体性能，并在包含大量轮次的IEMOCAP数据集上取得了最先进的性能。