Cluster-aware Pseudo-Labeling for Supervised Open Relation Extraction

Bin Duan, Shusen Wang, Xingxian Liu, Yajing Xu


Abstract
Supervised open relation extraction aims to discover novel relations by leveraging supervised data of pre-defined relations. However, most existing methods do not achieve effective knowledge transfer from pre-defined relations to novel relations, they have difficulties generating high-quality pseudo-labels for unsupervised data of novel relations and usually suffer from the error propagation issue. In this paper, we propose a Cluster-aware Pseudo-Labeling (CaPL) method to improve the pseudo-labels quality and transfer more knowledge for discovering novel relations. Specifically, the model is firstly pre-trained with the pre-defined relations to learn the relation representations. To improve the pseudo-labels quality, the distances between each instance and all cluster centers are used to generate the cluster-aware soft pseudo-labels for novel relations. To mitigate the catastrophic forgetting issue, we design the consistency regularization loss to make better use of the pseudo-labels and jointly train the model with both unsupervised and supervised data. Experimental results on two public datasets demonstrate that our proposed method achieves new state-of-the-arts performance.
Anthology ID:
2022.coling-1.158
Volume:
Proceedings of the 29th International Conference on Computational Linguistics
Month:
October
Year:
2022
Address:
Gyeongju, Republic of Korea
Venue:
COLING
SIG:
Publisher:
International Committee on Computational Linguistics
Note:
Pages:
1834–1841
Language:
URL:
https://aclanthology.org/2022.coling-1.158
DOI:
Bibkey:
Cite (ACL):
Bin Duan, Shusen Wang, Xingxian Liu, and Yajing Xu. 2022. Cluster-aware Pseudo-Labeling for Supervised Open Relation Extraction. In Proceedings of the 29th International Conference on Computational Linguistics, pages 1834–1841, Gyeongju, Republic of Korea. International Committee on Computational Linguistics.
Cite (Informal):
Cluster-aware Pseudo-Labeling for Supervised Open Relation Extraction (Duan et al., COLING 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.coling-1.158.pdf
Code
 bobtuan/capl
Data
TACRED