Exploiting Pseudo Future Contexts for Emotion Recognition in Conversations

TL;DR

This paper proposes generating pseudo future contexts using pre-trained language models to enhance emotion recognition in conversations, especially when real future contexts are unavailable, showing improved performance across multiple datasets.

Contribution

It introduces a novel framework that generates and integrates pseudo future contexts for ERC, addressing the challenge of unavailable real future contexts in real-world scenarios.

Findings

Pseudo future contexts can rival real ones in certain cases.

The method outperforms existing approaches on four ERC datasets.

Pseudo contexts are especially effective in context-independent conversations.

Abstract

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.