ACL Findings2024
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 1 on two benchmark datasets show that DENRL, using merely its own parametric distribution and simple data-driven heuristics, outperforms large language model-based baselines by a large margin with better interpretability.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
1 top-tier paper has cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
Cited by top-tier papers1
Builds on10
- A Joint Neural Model for Information Extraction with Global FeaturesYing Lin, Heng Ji, Fei Huang, Lingfei WuACL 2020 · 376 citations
- BOND: BERT-Assisted Open-Domain Named Entity Recognition with Distant SupervisionChen Liang, Yue Yu, Haoming Jiang, Siawpeng Er et al.KDD 2020 · 118 citations
- Integrating Deep Learning with Logic Fusion for Information ExtractionWenya Wang, Sinno Jialin PanAAAI 2020 · 55 citations
- Distantly-Supervised Named Entity Recognition with Noise-Robust Learning and Language Model Augmented Self-TrainingYu Meng, Yunyi Zhang, Jiaxin Huang, Xuan Wang et al.EMNLP 2021 · 50 citations
- Gradient Imitation Reinforcement Learning for Low Resource Relation ExtractionXuming Hu, Chenwei Zhang, Yawen Yang, Xiaohe Li et al.EMNLP 2021 · 42 citations
Related papers
- Joint Entity and Relation Extraction with a Hybrid Transformer and Reinforcement Learning Based ModelYa Xiao, Chengxiang Tan, Zhijie Fan, Qian Xu et al.AAAI 2020 · 33 citations
- OneRel: Joint Entity and Relation Extraction with One Module in One StepYuming Shang, Heyan Huang, Xianling MaoAAAI 2022 · 200 citations
- Relabel the Noise: Joint Extraction of Entities and Relations via Cooperative MultiagentsDaoyuan Chen, Yaliang Li, Kai Lei, Ying ShenACL 2020 · 13 citations
- REA: Robust Cross-lingual Entity Alignment Between Knowledge GraphsShichao Pei, Lu Yu, Guoxian Yu, Xiangliang ZhangKDD 2020 · 44 citations
- Improving Distantly-Supervised Named Entity Recognition with Self-Collaborative Denoising LearningXinghua Zhang, Bowen Yu, Tingwen Liu, Zhenyu Zhang et al.EMNLP Findings 2021 · 5 citations
