Exploiting Pseudo Future Contexts for Emotion Recognition in Conversations
This work addresses a practical limitation in emotion recognition for conversational AI by providing a method to simulate future contexts, though it is incremental as it builds on existing context-based approaches.
The paper tackles the problem of emotion recognition in conversations by generating pseudo future contexts to compensate for the unavailability of real future contexts in real-life scenarios, achieving superior performance on four datasets.
With the extensive accumulation of conversational data on the Internet, emotion recognition in conversations (ERC) has received increasing attention. Previous efforts of this task mainly focus on leveraging contextual and speaker-specific features, or integrating heterogeneous external commonsense knowledge. Among them, some heavily rely on future contexts, which, however, are not always available in real-life scenarios. This fact inspires us to generate pseudo future contexts to improve ERC. Specifically, for an utterance, we generate its future context with pre-trained language models, potentially containing extra beneficial knowledge in a conversational form homogeneous with the historical ones. These characteristics make pseudo future contexts easily fused with historical contexts and historical speaker-specific contexts, yielding a conceptually simple framework systematically integrating multi-contexts. Experimental results on four ERC datasets demonstrate our method's superiority. Further in-depth analyses reveal that pseudo future contexts can rival real ones to some extent, especially in relatively context-independent conversations.