Regularized Attentive Capsule Network for Overlapped Relation Extraction

Tianyi Liu, Xiangyu Lin, Weijia Jia, Mingliang Zhou, Wei Zhao

Abstract
Distantly supervised relation extraction has been widely applied in knowledge base construction due to its less requirement of human efforts. However, the automatically established training datasets in distant supervision contain low-quality instances with noisy words and overlapped relations, introducing great challenges to the accurate extraction of relations. To address this problem, we propose a novel Regularized Attentive Capsule Network (RA-CapNet) to better identify highly overlapped relations in each informal sentence. To discover multiple relation features in an instance, we embed multi-head attention into the capsule network as the low-level capsules, where the subtraction of two entities acts as a new form of relation query to select salient features regardless of their positions. To further discriminate overlapped relation features, we devise disagreement regularization to explicitly encourage the diversity among both multiple attention heads and low-level capsules. Extensive experiments conducted on widely used datasets show that our model achieves significant improvements in relation extraction.
Anthology ID:
2020.coling-main.562
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:
6388–6398
Language:
URL:
https://aclanthology.org/2020.coling-main.562
DOI:
10.18653/v1/2020.coling-main.562
Bibkey:
Cite (ACL):
Tianyi Liu, Xiangyu Lin, Weijia Jia, Mingliang Zhou, and Wei Zhao. 2020. Regularized Attentive Capsule Network for Overlapped Relation Extraction. In Proceedings of the 28th International Conference on Computational Linguistics, pages 6388–6398, Barcelona, Spain (Online). International Committee on Computational Linguistics.
Cite (Informal):
Regularized Attentive Capsule Network for Overlapped Relation Extraction (Liu et al., COLING 2020)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-4/2020.coling-main.562.pdf
PDF Search