Mimicking the Thinking Process for Emotion Recognition in Conversation with Prompts and Paraphrasing

TL;DR

This paper introduces a novel framework for emotion recognition in conversation that mimics human thinking by using prompts and paraphrasing to incorporate context, background, and subtle label differences, achieving superior results.

Contribution

The paper proposes a new framework that models conversational context, speaker background, and label semantics using prompts and paraphrasing, advancing emotion recognition methods.

Findings

Outperforms state-of-the-art baselines on three benchmarks.

Effectively incorporates context and background information.

Enhances understanding of subtle emotion label differences.

Abstract

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.