Directed Acyclic Graph Network for Conversational Emotion Recognition
This work addresses emotion recognition in conversations, which is important for applications like chatbots and social analysis, but it appears incremental as it combines existing graph-based and recurrence-based methods.
The paper tackled emotion recognition in conversations by proposing a directed acyclic graph network (DAG-ERC) to model conversation structure, achieving superior results on four benchmarks compared to state-of-the-art models.
The modeling of conversational context plays a vital role in emotion recognition from conversation (ERC). In this paper, we put forward a novel idea of encoding the utterances with a directed acyclic graph (DAG) to better model the intrinsic structure within a conversation, and design a directed acyclic neural network, namely DAG-ERC, to implement this idea. In an attempt to combine the strengths of conventional graph-based neural models and recurrence-based neural models, DAG-ERC provides a more intuitive way to model the information flow between long-distance conversation background and nearby context. Extensive experiments are conducted on four ERC benchmarks with state-of-the-art models employed as baselines for comparison. The empirical results demonstrate the superiority of this new model and confirm the motivation of the directed acyclic graph architecture for ERC.