The Emotion is Not One-hot Encoding: Learning with Grayscale Label for Emotion Recognition in Conversation. (arXiv:2206.07359v2 [cs.CL] UPDATED)

In emotion recognition in conversation (ERC), the emotion of the current
utterance is predicted by considering the previous context, which can be
utilized in many natural language processing tasks. Although multiple emotions
can coexist in a given sentence, most previous approaches take the perspective
of a classification task to predict only a given label. However, it is
expensive and difficult to label the emotion of a sentence with confidence or
multi-label. In this paper, we automatically construct a grayscale label …

arxiv conversation emotion encoding learning