中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
Semantic consistency: A local subspace based method for distant supervised relation extraction

文献类型:会议论文

作者Han, Xianpei (1) ; Sun, Le (1)
出版日期2014
会议名称52nd Annual Meeting of the Association for Computational Linguistics, ACL 2014
会议日期June 22, 2014 - June 27, 2014
会议地点Baltimore, MD, United states
页码718-724
中文摘要One fundamental problem of distant supervision is the noisy training corpus problem. In this paper, we propose a new distant supervision method, called Semantic Consistency, which can identify reliable instances from noisy instances by inspecting whether an instance is located in a semantically consistent region. Specifically, we propose a semantic consistency model, which first models the local subspace around an instance as a sparse linear combination of training instances, then estimate the semantic consistency by exploiting the characteristics of the local subspace. Experimental results verified the effectiveness of our method. © 2014 Association for Computational Linguistics.
英文摘要One fundamental problem of distant supervision is the noisy training corpus problem. In this paper, we propose a new distant supervision method, called Semantic Consistency, which can identify reliable instances from noisy instances by inspecting whether an instance is located in a semantically consistent region. Specifically, we propose a semantic consistency model, which first models the local subspace around an instance as a sparse linear combination of training instances, then estimate the semantic consistency by exploiting the characteristics of the local subspace. Experimental results verified the effectiveness of our method. © 2014 Association for Computational Linguistics.
收录类别EI
会议录出版地Association for Computational Linguistics (ACL)
语种英语
ISBN号9781937284732
源URL[http://ir.iscas.ac.cn/handle/311060/16630]  
专题软件研究所_软件所图书馆_会议论文
推荐引用方式
GB/T 7714
Han, Xianpei ,Sun, Le . Semantic consistency: A local subspace based method for distant supervised relation extraction[C]. 见:52nd Annual Meeting of the Association for Computational Linguistics, ACL 2014. Baltimore, MD, United states. June 22, 2014 - June 27, 2014.

入库方式: OAI收割

来源:软件研究所

浏览0
下载0
收藏0
其他版本

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。