GLaRA: Graph-based Labeling Rule Augmentation for Weakly Supervised Named Entity Recognition

Xinyan Zhao, Haibo Ding, Zhe Feng


Abstract
Instead of using expensive manual annotations, researchers have proposed to train named entity recognition (NER) systems using heuristic labeling rules. However, devising labeling rules is challenging because it often requires a considerable amount of manual effort and domain expertise. To alleviate this problem, we propose GLARA, a graph-based labeling rule augmentation framework, to learn new labeling rules from unlabeled data. We first create a graph with nodes representing candidate rules extracted from unlabeled data. Then, we design a new graph neural network to augment labeling rules by exploring the semantic relations between rules. We finally apply the augmented rules on unlabeled data to generate weak labels and train a NER model using the weakly labeled data. We evaluate our method on three NER datasets and find that we can achieve an average improvement of +20% F1 score over the best baseline when given a small set of seed rules.
Anthology ID:
2021.eacl-main.318
Volume:
Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume
Month:
April
Year:
2021
Address:
Online
Editors:
Paola Merlo, Jorg Tiedemann, Reut Tsarfaty
Venue:
EACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3636–3649
Language:
URL:
https://aclanthology.org/2021.eacl-main.318
DOI:
10.18653/v1/2021.eacl-main.318
Bibkey:
Cite (ACL):
Xinyan Zhao, Haibo Ding, and Zhe Feng. 2021. GLaRA: Graph-based Labeling Rule Augmentation for Weakly Supervised Named Entity Recognition. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pages 3636–3649, Online. Association for Computational Linguistics.
Cite (Informal):
GLaRA: Graph-based Labeling Rule Augmentation for Weakly Supervised Named Entity Recognition (Zhao et al., EACL 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.eacl-main.318.pdf
Code
 zhaoxy92/GLaRA
Data
BC5CDR