Distantly supervised relation extraction through a trade-off mechanism

Jun Ni, Yu Liu, Kai Wang, Zhehuan Zhao, Quan Z. Sheng

Research output: Chapter in Book/Report/Conference proceedingConference proceeding contribution

Abstract

Distantly supervised relation extraction can label large amounts of unstructured text without human annotations for training. However, distant supervision inevitably accompanies with the wrong labeling problem, which can deteriorate the performance of relation extraction. What's more, the entity-pair information, which can enrich instance information, is still underutilized. In the light of these issues, we propose TMNN, a novel Neural Network framework with a Trade-off Mechanism, which combines the feature of text and entity pair on the sentence level to predict relations. Our proposed trade-off mechanism is a probability generation module to dynamically adjust the weights of text and corresponding entity pair for each sentence. Experimental results on a widely used dataset show that the proposed method reduces the noisy labels and achieves substantial improvement over the state-of-the-art methods.

Original languageEnglish
Title of host publication2019 International Joint Conference on Neural Networks, IJCNN 2019
Place of PublicationPiscataway, NJ
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Pages1-7
Number of pages7
ISBN (Electronic)9781728119854
ISBN (Print)9781728119861
DOIs
Publication statusPublished - 1 Jul 2019
Event2019 International Joint Conference on Neural Networks, IJCNN 2019 - Budapest, Hungary
Duration: 14 Jul 201919 Jul 2019

Conference

Conference2019 International Joint Conference on Neural Networks, IJCNN 2019
CountryHungary
CityBudapest
Period14/07/1919/07/19

Fingerprint Dive into the research topics of 'Distantly supervised relation extraction through a trade-off mechanism'. Together they form a unique fingerprint.

Cite this