Distantly-Supervised Joint Extraction with Noise-Robust Learning

Yufei Li, Xiao Yu, Yanghong Guo, Yanchi Liu, Haifeng Chen, Cong Liu

Abstract
Joint entity and relation extraction is a process that identifies entity pairs and their relations using a single model. We focus on the problem of joint extraction in distantly-labeled data, whose labels are generated by aligning entity mentions with the corresponding entity and relation tags using a knowledge base (KB). One key challenge is the presence of noisy labels arising from both incorrect entity and relation annotations, which significantly impairs the quality of supervised learning. Existing approaches, either considering only one source of noise or making decisions using external knowledge, cannot well-utilize significant information in the training data. We propose DENRL, a generalizable framework that 1) incorporates a lightweight transformer backbone into a sequence labeling scheme for joint tagging, and 2) employs a noise-robust framework that regularizes the tagging model with significant relation patterns and entity-relation dependencies, then iteratively self-adapts to instances with less noise from both sources. Surprisingly, experiments on two benchmark datasets show that DENRL, using merely its own parametric distribution and simple data-driven heuristics, outperforms strong baselines by a large margin with better interpretability.
Anthology ID:
2024.findings-acl.607
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:
10202–10217
Language:
URL:
https://aclanthology.org/2024.findings-acl.607
DOI:
10.18653/v1/2024.findings-acl.607
Bibkey:
Cite (ACL):
Yufei Li, Xiao Yu, Yanghong Guo, Yanchi Liu, Haifeng Chen, and Cong Liu. 2024. Distantly-Supervised Joint Extraction with Noise-Robust Learning. In Findings of the Association for Computational Linguistics: ACL 2024, pages 10202–10217, Bangkok, Thailand. Association for Computational Linguistics.
Cite (Informal):
Distantly-Supervised Joint Extraction with Noise-Robust Learning (Li et al., Findings 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/add_acl24_videos/2024.findings-acl.607.pdf
PDF Search