TED: Turn Emphasis with Dialogue Feature Attention for Emotion Recognition in Conversation
This addresses emotion recognition in multi-turn conversations, offering an incremental improvement over existing methods.
The paper tackled emotion recognition in conversation by proposing TED, a priority-based attention method that uses dialogue features to explicitly distinguish turns, achieving state-of-the-art performance on the IEMOCAP dataset.
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.