GAN Driven Semi-distant Supervision for Relation Extraction

Pengshuai Li, Xinsong Zhang, Weijia Jia, Hai Zhao


Abstract
Distant supervision has been widely used in relation extraction tasks without hand-labeled datasets recently. However, the automatically constructed datasets comprise numbers of wrongly labeled negative instances due to the incompleteness of knowledge bases, which is neglected by current distant supervised methods resulting in seriously misleading in both training and testing processes. To address this issue, we propose a novel semi-distant supervision approach for relation extraction by constructing a small accurate dataset and properly leveraging numerous instances without relation labels. In our approach, we construct accurate instances by both knowledge base and entity descriptions determined to avoid wrong negative labeling and further utilize unlabeled instances sufficiently using generative adversarial network (GAN) framework. Experimental results on real-world datasets show that our approach can achieve significant improvements in distant supervised relation extraction over strong baselines.
Anthology ID:
N19-1307
Volume:
Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)
Month:
June
Year:
2019
Address:
Minneapolis, Minnesota
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3026–3035
Language:
URL:
https://aclanthology.org/N19-1307
DOI:
10.18653/v1/N19-1307
Bibkey:
Cite (ACL):
Pengshuai Li, Xinsong Zhang, Weijia Jia, and Hai Zhao. 2019. GAN Driven Semi-distant Supervision for Relation Extraction. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 3026–3035, Minneapolis, Minnesota. Association for Computational Linguistics.
Cite (Informal):
GAN Driven Semi-distant Supervision for Relation Extraction (Li et al., NAACL 2019)
Copy Citation:
PDF:
https://preview.aclanthology.org/update-css-js/N19-1307.pdf
Video:
 https://vimeo.com/355832634