Improving short-text representation in convolutional networks by dependency parsing

doi:10.1007/s10115-018-1312-9

	Improving short-text representation in convolutional networks by dependency parsing
	Zhang, Siheng; Zhang, Wensheng; Niu, Jinghao
刊名	KNOWLEDGE AND INFORMATION SYSTEMS
	2019-10-01
卷号	61 期号:1 页码:463-484
关键词	Convolutional neural network Dependency parsing Question answering system Question classification Semantic equivalence
ISSN号	0219-1377
DOI	10.1007/s10115-018-1312-9
通讯作者	Zhang, Wensheng(zhangwenshengia@hotmail.com)
英文摘要	Automatic question answering (QA) system is the inevitable trend of future search engines. As the essential steps of QA, question classification and text retrieval both require algorithms to capture the semantic information and syntactic structure of natural language. This paper proposes dependency-based convolutional networks to learn a representation of sentences. First, we use dependency layer to map discrete word depth on the dependency tree of a sentence into continuous real space. Then, the mapping result serves as weight of word vectors and convolutional kernels are employed as feature extractors for further specific tasks. The method proposed allows convolutional networks to take the advantage of higher representational ability of dependency structure. Experiments involving three tasks including text classification, duplicate classification and text pairs ranking confirm the advantages of our model.
资助项目	National Natural Science Foundation of China[U1636220] ; National Natural Science Foundation of China[61432008] ; National Natural Science Foundation of China[61472423] ; Huawei Innovation Research Program[HO2017050001BI] ; Beijing Natural Science Foundation[4172063]
WOS关键词	GENERIC CLINICAL QUESTIONS ; TAXONOMY
WOS研究方向	Computer Science
语种	英语
出版者	SPRINGER LONDON LTD
WOS记录号	WOS:000483698200017
资助机构	National Natural Science Foundation of China ; Huawei Innovation Research Program ; Beijing Natural Science Foundation
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/27229]
专题	中国科学院自动化研究所
通讯作者	Zhang, Wensheng
作者单位	Univ Chinese Acad Sci, Sch Comp & Control Engn, Inst Automat, Chinese Acad Sci, 95 Zhongguancun East Rd, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Zhang, Siheng,Zhang, Wensheng,Niu, Jinghao. Improving short-text representation in convolutional networks by dependency parsing[J]. KNOWLEDGE AND INFORMATION SYSTEMS,2019,61(1):463-484.
APA	Zhang, Siheng,Zhang, Wensheng,&Niu, Jinghao.(2019).Improving short-text representation in convolutional networks by dependency parsing.KNOWLEDGE AND INFORMATION SYSTEMS,61(1),463-484.
MLA	Zhang, Siheng,et al."Improving short-text representation in convolutional networks by dependency parsing".KNOWLEDGE AND INFORMATION SYSTEMS 61.1(2019):463-484.