Employing Contrastive Strategies for Multi-label Textual Emotion Recognition - Intelligent Information Processing XI Access content directly
Conference Papers Year : 2022

Employing Contrastive Strategies for Multi-label Textual Emotion Recognition

Yangyang Zhou
  • Function : Author
  • PersonId : 1275129
Xin Kang
  • Function : Author
  • PersonId : 1275130
Fuji Ren
  • Function : Author
  • PersonId : 1275131

Abstract

Textual emotion recognition is an important part of the human-computer interaction field. Current methods of textual emotion recognition mainly use large-scale pre-trained models fine-tuning. However, these methods are not accurate enough in the semantic representation of sentences. Contrastive learning has been shown to optimize the representation of vectors in the feature space. Therefore, we introduce the contrastive strategies to the textual emotion recognition task. We propose two approaches: using self-supervised contrastive learning before fine-tuning the pre-trained model, and using contrastive training on the same inputs during fine-tuning. We experiment on two multi-label emotion classification datasets: Ren-CECps and NLPCC2018. The experimental results demonstrate that the latter contrastive approach effectively improves the accuracy of emotion recognition.
Embargoed file
Embargoed file
0 7 12
Year Month Jours
Avant la publication
Wednesday, January 1, 2025
Embargoed file
Wednesday, January 1, 2025
Please log in to request access to the document

Dates and versions

hal-04178710 , version 1 (08-08-2023)

Licence

Attribution

Identifiers

Cite

Yangyang Zhou, Xin Kang, Fuji Ren. Employing Contrastive Strategies for Multi-label Textual Emotion Recognition. 12th International Conference on Intelligent Information Processing (IIP), May 2022, Qingdao, China. pp.299-310, ⟨10.1007/978-3-031-03948-5_24⟩. ⟨hal-04178710⟩
10 View
0 Download

Altmetric

Share

Gmail Facebook X LinkedIn More