A Relation-Oriented Clustering Method for Open Relation Extraction

Jun Zhao, Tao Gui, Qi Zhang, Yaqian Zhou


Abstract
The clustering-based unsupervised relation discovery method has gradually become one of the important methods of open relation extraction (OpenRE). However, high-dimensional vectors can encode complex linguistic information which leads to the problem that the derived clusters cannot explicitly align with the relational semantic classes. In this work, we propose a relation-oriented clustering model and use it to identify the novel relations in the unlabeled data. Specifically, to enable the model to learn to cluster relational data, our method leverages the readily available labeled data of pre-defined relations to learn a relation-oriented representation. We minimize distance between the instance with same relation by gathering the instances towards their corresponding relation centroids to form a cluster structure, so that the learned representation is cluster-friendly. To reduce the clustering bias on predefined classes, we optimize the model by minimizing a joint objective on both labeled and unlabeled data. Experimental results show that our method reduces the error rate by 29.2% and 15.7%, on two datasets respectively, compared with current SOTA methods.
Anthology ID:
2021.emnlp-main.765
Volume:
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2021
Address:
Online and Punta Cana, Dominican Republic
Editors:
Marie-Francine Moens, Xuanjing Huang, Lucia Specia, Scott Wen-tau Yih
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
9707–9718
Language:
URL:
https://aclanthology.org/2021.emnlp-main.765
DOI:
10.18653/v1/2021.emnlp-main.765
Bibkey:
Cite (ACL):
Jun Zhao, Tao Gui, Qi Zhang, and Yaqian Zhou. 2021. A Relation-Oriented Clustering Method for Open Relation Extraction. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 9707–9718, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
Cite (Informal):
A Relation-Oriented Clustering Method for Open Relation Extraction (Zhao et al., EMNLP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.emnlp-main.765.pdf
Video:
 https://aclanthology.org/2021.emnlp-main.765.mp4
Code
 ac-zyx/rocore
Data
FewRel