ToHRE: A Top-Down Classification Strategy with Hierarchical Bag Representation for Distantly Supervised Relation Extraction

Erxin Yu, Wenjuan Han, Yuan Tian, Yi Chang


Abstract
Distantly Supervised Relation Extraction (DSRE) has proven to be effective to find relational facts from texts, but it still suffers from two main problems: the wrong labeling problem and the long-tail problem. Most of the existing approaches address these two problems through flat classification, which lacks hierarchical information of relations. To leverage the informative relation hierarchies, we formulate DSRE as a hierarchical classification task and propose a novel hierarchical classification framework, which extracts the relation in a top-down manner. Specifically, in our proposed framework, 1) we use a hierarchically-refined representation method to achieve hierarchy-specific representation; 2) a top-down classification strategy is introduced instead of training a set of local classifiers. The experiments on NYT dataset demonstrate that our approach significantly outperforms other state-of-the-art approaches, especially for the long-tail problem.
Anthology ID:
2020.coling-main.146
Volume:
Proceedings of the 28th International Conference on Computational Linguistics
Month:
December
Year:
2020
Address:
Barcelona, Spain (Online)
Editors:
Donia Scott, Nuria Bel, Chengqing Zong
Venue:
COLING
SIG:
Publisher:
International Committee on Computational Linguistics
Note:
Pages:
1665–1676
Language:
URL:
https://aclanthology.org/2020.coling-main.146
DOI:
10.18653/v1/2020.coling-main.146
Bibkey:
Cite (ACL):
Erxin Yu, Wenjuan Han, Yuan Tian, and Yi Chang. 2020. ToHRE: A Top-Down Classification Strategy with Hierarchical Bag Representation for Distantly Supervised Relation Extraction. In Proceedings of the 28th International Conference on Computational Linguistics, pages 1665–1676, Barcelona, Spain (Online). International Committee on Computational Linguistics.
Cite (Informal):
ToHRE: A Top-Down Classification Strategy with Hierarchical Bag Representation for Distantly Supervised Relation Extraction (Yu et al., COLING 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.coling-main.146.pdf