Enhancing Multi-Label Text Classification under Label-Dependent Noise: A Label-Specific Denoising Framework

Pengyu Xu, Liping Jing, Jian Yu


Abstract
Recent advancements in noisy multi-label text classification have primarily relied on the class-conditional noise (CCN) assumption, which treats each label independently undergoing label flipping to generate noisy labels. However, in real-world scenarios, noisy labels often exhibit dependencies with true labels. In this study, we validate through hypothesis testing that real-world datasets are unlikely to adhere to the CCN assumption, indicating that label noise is dependent on the labels. To address this, we introduce a label-specific denoising framework designed to counteract label-dependent noise. The framework initially presents a holistic selection metric that evaluates noisy labels by concurrently considering loss information, ranking information, and feature centroid. Subsequently, it identifies and corrects noisy labels individually for each label category in a fine-grained manner. Extensive experiments on benchmark datasets demonstrate the effectiveness of our method under both synthetic and real-world noise conditions, significantly improving performance over existing state-of-the-art models.
Anthology ID:
2024.findings-emnlp.324
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2024
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
5674–5688
Language:
URL:
https://preview.aclanthology.org/icon-24-ingestion/2024.findings-emnlp.324/
DOI:
10.18653/v1/2024.findings-emnlp.324
Bibkey:
Cite (ACL):
Pengyu Xu, Liping Jing, and Jian Yu. 2024. Enhancing Multi-Label Text Classification under Label-Dependent Noise: A Label-Specific Denoising Framework. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 5674–5688, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
Enhancing Multi-Label Text Classification under Label-Dependent Noise: A Label-Specific Denoising Framework (Xu et al., Findings 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/icon-24-ingestion/2024.findings-emnlp.324.pdf