[go: up one dir, main page]
More Web Proxy on the site http://driver.im/

Enhancing Contrastive Learning with Noise-Guided Attack: Towards Continual Relation Extraction in the Wild

Ting Wu, Jingyi Liu, Rui Zheng, Tao Gui, Qi Zhang, Xuanjing Huang


Abstract
The principle of continual relation extraction (CRE) involves adapting to emerging novel relations while preserving old knowledge. Existing CRE approaches excel in preserving old knowledge but falter when confronted with contaminated data streams, likely due to an artificial assumption of no annotation errors. Recognizing the prevalence of noisy labels in real-world datasets, we introduce a more practical learning scenario, termed as noisy-CRE. In response to this challenge, we propose a noise-resistant contrastive framework called Noise-guided Attack in Contrastive Learning (NaCL), aimed at learning incremental corrupted relations. Diverging from conventional approaches like sample discarding or relabeling in the presence of noisy labels, NaCL takes a transformative route by modifying the feature space through targeted attack. This attack aims to align the feature space with the provided, albeit inaccurate, labels, thereby enhancing contrastive representations. Extensive empirical validations demonstrate the consistent performance improvement of NaCL with increasing noise rates, surpassing state-of-the-art methods.
Anthology ID:
2024.acl-long.121
Volume:
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
August
Year:
2024
Address:
Bangkok, Thailand
Editors:
Lun-Wei Ku, Andre Martins, Vivek Srikumar
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2227–2239
Language:
URL:
https://aclanthology.org/2024.acl-long.121
DOI:
10.18653/v1/2024.acl-long.121
Bibkey:
Cite (ACL):
Ting Wu, Jingyi Liu, Rui Zheng, Tao Gui, Qi Zhang, and Xuanjing Huang. 2024. Enhancing Contrastive Learning with Noise-Guided Attack: Towards Continual Relation Extraction in the Wild. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 2227–2239, Bangkok, Thailand. Association for Computational Linguistics.
Cite (Informal):
Enhancing Contrastive Learning with Noise-Guided Attack: Towards Continual Relation Extraction in the Wild (Wu et al., ACL 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.acl-long.121.pdf