Regularized Attentive Capsule Network for Overlapped Relation Extraction

Tianyi LIU, Xiangyu LIN, Weijia JIA*, Mingliang ZHOU, Wei ZHAO

*Corresponding author for this work

Research output: Book Chapters | Papers in Conference ProceedingsConference paper (refereed)Researchpeer-review

9 Citations (Scopus)

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.

Original languageEnglish
Title of host publicationCOLING 2020 : 28th International Conference on Computational Linguistics, Proceedings of the Conference
EditorsDonia SCOTT, Nuria BEL, Chengqing ZONG
PublisherAssociation for Computational Linguistics (ACL)
Pages6388-6398
Number of pages11
ISBN (Electronic)9781952148279
DOIs
Publication statusPublished - Dec 2020
Externally publishedYes
Event28th International Conference on Computational Linguistics, COLING 2020 - Virtual, Online, Spain
Duration: 8 Dec 202013 Dec 2020

Conference

Conference28th International Conference on Computational Linguistics, COLING 2020
Country/TerritorySpain
CityVirtual, Online
Period8/12/2013/12/20

Bibliographical note

Publisher Copyright:
© 2020 COLING 2020 - 28th International Conference on Computational Linguistics, Proceedings of the Conference. All rights reserved.

Fingerprint

Dive into the research topics of 'Regularized Attentive Capsule Network for Overlapped Relation Extraction'. Together they form a unique fingerprint.

Cite this