Structural block driven enhanced convolutional neural representation for relation extraction

doi:10.1016/j.asoc.2019.105913

CORC > 自动化研究所 > 中国科学院自动化研究所 > 类脑智能研究中心 > 类脑认知计算

	Structural block driven enhanced convolutional neural representation for relation extraction
	Wang, Dongsheng 5; Tiwari, Prayag 1; Garg, Sahil 2; Zhu, Hongyin 3; Bruza, Peter 4
刊名	APPLIED SOFT COMPUTING
	2020
卷号	86 页码:9
关键词	Relation extraction Deep learning CNNs Dependency parsing
ISSN号	1568-4946
DOI	10.1016/j.asoc.2019.105913
通讯作者	Tiwari, Prayag(prayag.tiwari@dei.unipd.it)
英文摘要	In this paper, we propose a novel lightweight relation extraction approach of structural block driven convolutional neural learning. Specifically, we detect the essential sequential tokens associated with entities through dependency analysis, named as a structural block, and only encode the block on a block-wise and an inter-block-wise representation, utilizing multi-scale Convolutional Neural Networks (CNNs). This is to (1) eliminate the noisy from irrelevant part of a sentence; meanwhile (2) enhance the relevant block representation with both block-wise and inter-block-wise semantically enriched representation. Our method has the advantage of being independent of long sentence context since we only encode the sequential tokens within a block boundary. Experiments on two datasets i.e., SemEval2010 and KBP37, demonstrate the significant advantages of our method. In particular, we achieve the new state-of-the-art performance on the KBP37 dataset; and comparable performance with the state-of-the-art on the SemEval2010 dataset. (C) 2019 Elsevier B.V. All rights reserved.
资助项目	European Union's Horizon 2020 research and innovation programme under the Marie Sklodowska-Curie grant[721321]
WOS关键词	ANOMALY DETECTION
WOS研究方向	Computer Science
语种	英语
出版者	ELSEVIER
WOS记录号	WOS:000503388200064
资助机构	European Union's Horizon 2020 research and innovation programme under the Marie Sklodowska-Curie grant
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/29451]
专题	类脑智能研究中心_类脑认知计算
通讯作者	Tiwari, Prayag
作者单位	1.Univ Padua, Dept Informat Engn, Padua, Italy 2.Ecole Technol Super, Montreal, PQ H3C 1K3, Canada 3.Chinese Acad Sci, Inst Automat, Beijing, Peoples R China 4.Queensland Univ Technol, Sch Informat Syst, 2 George St, Brisbane, Qld 4000, Australia 5.Univ Copenhagen, Dept Comp Sci, Copenhagen, Denmark
推荐引用方式 GB/T 7714	Wang, Dongsheng,Tiwari, Prayag,Garg, Sahil,et al. Structural block driven enhanced convolutional neural representation for relation extraction[J]. APPLIED SOFT COMPUTING,2020,86:9.
APA	Wang, Dongsheng,Tiwari, Prayag,Garg, Sahil,Zhu, Hongyin,&Bruza, Peter.(2020).Structural block driven enhanced convolutional neural representation for relation extraction.APPLIED SOFT COMPUTING,86,9.
MLA	Wang, Dongsheng,et al."Structural block driven enhanced convolutional neural representation for relation extraction".APPLIED SOFT COMPUTING 86(2020):9.