Mimicking the Thinking Process for Emotion Recognition in Conversation with Prompts and Paraphrasing
This addresses the challenging problem of accurately predicting emotions in conversations for applications like human-computer interaction, though it appears incremental by building on existing prompt-based methods.
The paper tackles emotion recognition in conversation by proposing a framework that mimics human thinking to model conversational context, speaker background, and subtle emotion label differences, achieving state-of-the-art results on three benchmarks.
Emotion recognition in conversation, which aims to predict the emotion for all utterances, has attracted considerable research attention in recent years. It is a challenging task since the recognition of the emotion in one utterance involves many complex factors, such as the conversational context, the speaker's background, and the subtle difference between emotion labels. In this paper, we propose a novel framework which mimics the thinking process when modeling these factors. Specifically, we first comprehend the conversational context with a history-oriented prompt to selectively gather information from predecessors of the target utterance. We then model the speaker's background with an experience-oriented prompt to retrieve the similar utterances from all conversations. We finally differentiate the subtle label semantics with a paraphrasing mechanism to elicit the intrinsic label related knowledge. We conducted extensive experiments on three benchmarks. The empirical results demonstrate the superiority of our proposed framework over the state-of-the-art baselines.