题名 | GAN driven semi-distant supervision for relation extraction |
作者 | |
发表日期 | 2019 |
会议名称 | 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2019 |
会议录名称 | NAACL HLT 2019 - 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies - Proceedings of the Conference
![]() |
ISBN | 978-195073713-0 |
卷号 | 1 |
页码 | 3026-3035 |
会议日期 | June 2-7, 2019 |
会议地点 | Minneapolis, MN, USA |
出版者 | Association for Computational Linguistics (ACL) |
摘要 | 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. © 2019 Association for Computational Linguistics |
URL | 查看来源 |
语种 | 英语English |
引用统计 | |
文献类型 | 会议论文 |
条目标识符 | https://repository.uic.edu.cn/handle/39GCC9TT/4480 |
专题 | 个人在本单位外知识产出 |
作者单位 | 1.Dept. of CSE, Shanghai Jiao Tong University, Shanghai, China 2.State Key Lab of IoT for Smart City, CIS, University of Macau, Macau, China |
推荐引用方式 GB/T 7714 | Li, Pengshuai,Zhang, Xinsong,Jia, Weijiaet al. GAN driven semi-distant supervision for relation extraction[C]: Association for Computational Linguistics (ACL), 2019: 3026-3035. |
条目包含的文件 | 条目无相关文件。 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论