Distant supervision for relation extraction with hierarchical selective attention | |
Zhou, Peng![]() ![]() ![]() ![]() ![]() ![]() | |
刊名 | NEURAL NETWORKS
![]() |
2018-12-01 | |
期号 | 108页码:240-247 |
关键词 | Relation Extraction Distant Supervision Hierarchical Attention Piecewise Convolutional Neural Networks |
ISSN号 | 0893-6080 |
英文摘要 | Distant supervised relation extraction is an important task in the field of natural language processing. There are two main shortcomings for most state-of-the-art methods. One is that they take all sentences of an entity pair as input, which would result in a large computational cost. But in fact, few of most relevant sentences are enough to recognize the relation of an entity pair. To tackle these problems, we propose a novel hierarchical selective attention network for relation extraction under distant supervision. Our model first selects most relevant sentences by taking coarse sentence-level attention on all sentences of an entity pair and then employs word-level attention to construct sentence representations and fine sentence-level attention to aggregate these sentence representations. Experimental results on a widely used dataset demonstrate that our method performs significantly better than most of existing methods. (C) 2018 Elsevier Ltd. All rights reserved |
语种 | 英语 |
内容类型 | 期刊论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/26081] ![]() |
专题 | 数字内容技术与服务研究中心_听觉模型与认知计算 |
通讯作者 | Qi,Zhenyu |
作者单位 | CASIA |
推荐引用方式 GB/T 7714 | Zhou, Peng,Xu, Jiaming,Qi,Zhenyu,et al. Distant supervision for relation extraction with hierarchical selective attention[J]. NEURAL NETWORKS,2018(108):240-247. |
APA | Zhou, Peng,Xu, Jiaming,Qi,Zhenyu,Bao, Hongyun,Chen,Zhineng,&Xu, Bo.(2018).Distant supervision for relation extraction with hierarchical selective attention.NEURAL NETWORKS(108),240-247. |
MLA | Zhou, Peng,et al."Distant supervision for relation extraction with hierarchical selective attention".NEURAL NETWORKS .108(2018):240-247. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
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