SELP: A Semantically-Driven Approach for Separated and Accurate Class Prototypes in Few-Shot Text Classification

Wenxin Liang, Tingyu Zhang, Han Liu, Feng Zhang

Abstract
The meta-learning paradigm has demonstrated significant effectiveness in few-shot text classification. Currently, numerous efforts are grounded in metric-based learning, utilizing textual feature vectors for classification, with a common emphasis on enlarging inter-class distances to achieve improved classification effectiveness. However, many methods predominantly focus on enhancing the separation of prototypes without taking the semantic relationships between prototypes and class clusters into consideration. This oversight results in incomplete and inaccurate encoding of prototypes within the semantic space, affecting the generality of the learned metric space. In this paper, we propose the utilization of Semantically Enhanced Labels for calibrating class Prototypes (SELP), thereby obtaining prototypes that are more separated and semantically accurate. Additionally, we have devised a center loss to enhance intra-class compactness, coupled with the introduction of a simulated label distribution method to address the overfitting problem. Extensive experiments on eight few-shot text classification datasets show that the proposed method outperforms baselines significantly. Our code is available at https://github.com/tttyyyzzz-zty/SELP.git.
Anthology ID:
2024.findings-acl.579
Volume:
Findings of the Association for Computational Linguistics: ACL 2024
Month:
August
Year:
2024
Address:
Bangkok, Thailand
Editors:
Lun-Wei Ku, Andre Martins, Vivek Srikumar
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
9732–9741
Language:
URL:
https://aclanthology.org/2024.findings-acl.579
DOI:
10.18653/v1/2024.findings-acl.579
Bibkey:
Cite (ACL):
Wenxin Liang, Tingyu Zhang, Han Liu, and Feng Zhang. 2024. SELP: A Semantically-Driven Approach for Separated and Accurate Class Prototypes in Few-Shot Text Classification. In Findings of the Association for Computational Linguistics: ACL 2024, pages 9732–9741, Bangkok, Thailand. Association for Computational Linguistics.
Cite (Informal):
SELP: A Semantically-Driven Approach for Separated and Accurate Class Prototypes in Few-Shot Text Classification (Liang et al., Findings 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/add_acl24_videos/2024.findings-acl.579.pdf
PDF Search