Chi Lok U, Simon, He, Jie, Gutierrez Basulto, Victor  ORCID: https://orcid.org/0000-0002-6117-5459 and Pan, Jeff Z.
2023.
Instances and labels: Hierarchy-aware joint supervised contrastive learning for hierarchical multi-label text classification.
Presented at: 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP),
Singapore,
06 -10 December 2023.
Findings of the Association for Computational Linguistics: EMNLP 2023.
ACL,
pp. 8858-8875.
10.18653/v1/2023.findings-emnlp.594
|
Preview |
PDF
- Published Version
Available under License Creative Commons Attribution. Download (1MB) | Preview |
Abstract
Hierarchical multi-label text classification (HMTC) aims at utilizing a label hierarchy in multi-label classification. Recent approaches to HMTC deal with the problem of imposing an overconstrained premise on the output space by using contrastive learning on generated samples in a semi-supervised manner to bring text and label embeddings closer. However, the generation of samples tends to introduce noise as it ignores the correlation between similar samples in the same batch. One solution to this issue is supervised contrastive learning, but it remains an underexplored topic in HMTC due to its complex structured labels. To overcome this challenge, we propose **HJCL**, a **H**ierarchy-aware **J**oint Supervised **C**ontrastive **L**earning method that bridges the gap between supervised contrastive learning and HMTC. Specifically, we employ both instance-wise and label-wise contrastive learning techniques and carefully construct batches to fulfill the contrastive learning objective. Extensive experiments on four multi-path HMTC datasets demonstrate that HJCLachieves promising results and the effectiveness of Contrastive Learning on HMTC. Code and data are available at https://github.com/simonucl/HJCL.
| Item Type: | Conference or Workshop Item - published (Paper) |
|---|---|
| Date Type: | Published Online |
| Status: | Published |
| Schools: | Schools > Computer Science & Informatics |
| Publisher: | ACL |
| Date of First Compliant Deposit: | 24 October 2023 |
| Date of Acceptance: | 7 October 2023 |
| Last Modified: | 16 Apr 2026 09:10 |
| URI: | https://orca.cardiff.ac.uk/id/eprint/163461 |
Actions (repository staff only)
 |
Edit Item |
Altmetric
Altmetric