Emotion Transfer with Enhanced Prototype for Unseen Emotion Recognition in Conversation

2025-08-26

AI Summary

Existing Emotion Recognition in Conversations (ERC) methods rely heavily on closed-domain assumptions and struggle to generalize to unseen emotions—a critical limitation for real-world deployment. Method: This paper introduces the novel task of Unseen Emotion Recognition in Conversations (UERC), establishing an open-domain ERC paradigm. We propose ProEmoTrans, a framework that (i) leverages large language models to enrich emotion semantic descriptions, (ii) incorporates a parameter-free encoding mechanism for efficient long-conversation modeling, and (iii) enhances Attention-Viterbi decoding to accurately capture emotion transitions and implicit expressions. Its core innovation is a prototype-based emotion transfer mechanism enabling cross-category knowledge transfer. Contribution/Results: Extensive experiments on three benchmark datasets demonstrate substantial improvements over state-of-the-art baselines, establishing the first strong baseline for UERC and advancing ERC toward practical open-domain applications.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: Generation
• Humans and AI: Emotional Intelligence

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• User Modeling, Personalization and Recommendation: Accountability, Transparency, and Ethics for personalization
• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search

Abstract

Current Emotion Recognition in Conversation (ERC) research follows a closed-domain assumption. However, there is no clear consensus on emotion classification in psychology, which presents a challenge for models when it comes to recognizing previously unseen emotions in real-world applications. To bridge this gap, we introduce the Unseen Emotion Recognition in Conversation (UERC) task for the first time and propose ProEmoTrans, a solid prototype-based emotion transfer framework. This prototype-based approach shows promise but still faces key challenges: First, implicit expressions complicate emotion definition, which we address by proposing an LLM-enhanced description approach. Second, utterance encoding in long conversations is difficult, which we tackle with a proposed parameter-free mechanism for efficient encoding and overfitting prevention. Finally, the Markovian flow nature of emotions is hard to transfer, which we address with an improved Attention Viterbi Decoding (AVD) method to transfer seen emotion transitions to unseen emotions. Extensive experiments on three datasets show that our method serves as a strong baseline for preliminary exploration in this new area.

Problem

• Recognizing unseen emotions in conversations beyond closed-domain assumptions
• Addressing implicit emotion expressions through LLM-enhanced description approach
• Transferring seen emotion transitions to unseen emotions using improved decoding

Innovation

• LLM-enhanced emotion description approach
• Parameter-free utterance encoding mechanism
• Improved Attention Viterbi Decoding method