Noisy Multi-Label Text Classification via Instance-Label Pair Correction

Pengyu Xu, Mingyang Song, Linkaida Liu, Bing Liu, Hongjian Sun, Liping Jing, Jian Yu


Abstract
In noisy label learning, instance selection based on small-loss criteria has been proven to be highly effective. However, in the case of noisy multi-label text classification (NMLTC), the presence of noise is not limited to the instance-level but extends to the (instance-label) pair-level.This gives rise to two main challenges.(1) The loss information at the pair-level fails to capture the variations between instances. (2) There are two types of noise at the pair-level: false positives and false negatives. Identifying false negatives from a large pool of negative pairs presents an exceedingly difficult task. To tackle these issues, we propose a novel approach called instance-label pair correction (iLaCo), which aims to address the problem of noisy pair selection and correction in NMLTC tasks.Specifically, we first introduce a holistic selection metric that identifies noisy pairs by simultaneously considering global loss information and instance-specific ranking information.Secondly, we employ a filter guided by label correlation to focus exclusively on negative pairs with label relevance. This filter significantly reduces the difficulty of identifying false negatives.Experimental analysis indicates that our framework effectively corrects noisy pairs in NMLTC datasets, leading to a significant improvement in model performance.
Anthology ID:
2024.findings-naacl.93
Volume:
Findings of the Association for Computational Linguistics: NAACL 2024
Month:
June
Year:
2024
Address:
Mexico City, Mexico
Editors:
Kevin Duh, Helena Gomez, Steven Bethard
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1446–1458
Language:
URL:
https://aclanthology.org/2024.findings-naacl.93
DOI:
Bibkey:
Cite (ACL):
Pengyu Xu, Mingyang Song, Linkaida Liu, Bing Liu, Hongjian Sun, Liping Jing, and Jian Yu. 2024. Noisy Multi-Label Text Classification via Instance-Label Pair Correction. In Findings of the Association for Computational Linguistics: NAACL 2024, pages 1446–1458, Mexico City, Mexico. Association for Computational Linguistics.
Cite (Informal):
Noisy Multi-Label Text Classification via Instance-Label Pair Correction (Xu et al., Findings 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.findings-naacl.93.pdf
Copyright:
 2024.findings-naacl.93.copyright.pdf