SEC: Context-Aware Metric Learning for Efficient Emotion Recognition in Conversation - Archive ouverte HAL
Communication Dans Un Congrès Année : 2024

SEC: Context-Aware Metric Learning for Efficient Emotion Recognition in Conversation

Résumé

The advent of deep learning models has made a considerable contribution to the achievement of Emotion Recognition in Conversation (ERC). However, this task still remains an important challenge due to the plurality and subjectivity of human emotions. Previous work on ERC provides predictive models using mostly graph-based conversation representations. In this work, we propose a way to model the conversational context that we incorporate into a metric learning training strategy, with a two-step process. This allows us to perform ERC in a flexible classification scenario and end up with a lightweight yet efficient model. Using metric learning through a Siamese Network architecture, we achieve 57.71 in macro F1 score for emotion classification in conversation on Daily-Dialog dataset, which outperforms the related work. This state-of-the-art result is promising in terms of the use of metric learning for emotion recognition, yet perfectible compared to the micro F1 score obtained.
Fichier principal
Vignette du fichier
gendron_sec-2024.wassa-1.2.pdf (1.04 Mo) Télécharger le fichier
Origine Fichiers éditeurs autorisés sur une archive ouverte
Licence

Dates et versions

hal-04702997 , version 1 (19-09-2024)

Licence

Identifiants

  • HAL Id : hal-04702997 , version 1

Citer

Barbara Gendron, Gaël Guibon. SEC: Context-Aware Metric Learning for Efficient Emotion Recognition in Conversation. Proceedings of the 14th Workshop on Computational Approaches to Subjectivity, Sentiment, & Social Media Analysis (WASSA at ACL 2024), Aug 2024, Bangkok, Thailand. ⟨hal-04702997⟩
31 Consultations
12 Téléchargements

Partager

More