Fuzzy fingerprints derived from PLM embeddings serve as interpretable emotion prototypes that reduce neutral overclassification in ERC while maintaining state-of-the-art performance and aligning with human judgments.
In: Kondrak G, Watanabe T (eds) Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Fuzzy Fingerprinting Encoder Pre-trained Language Models for Emotion Recognition in Conversations: Human Assessment and Validity Study
Fuzzy fingerprints derived from PLM embeddings serve as interpretable emotion prototypes that reduce neutral overclassification in ERC while maintaining state-of-the-art performance and aligning with human judgments.