CASIA OpenIR  > 数字内容技术与服务研究中心  > 听觉模型与认知计算
Semantic expansion using word embedding clustering and convolutional neural network for improving short text classification
Wang, Peng1; Xu, Bo1; Xu, Jiaming1; Tian, Guanhua1; Liu, Cheng-Lin1,2; Hao, Hongwei1
Source PublicationNEUROCOMPUTING
2016-01-22
Volume174Pages:806-814
SubtypeArticle
AbstractText classification can help users to effectively handle and exploit useful information hidden in large-scale documents. However, the sparsity of data and the semantic sensitivity to context often hinder the classification performance of short texts. In order to overcome the weakness, we propose a unified framework to expand short texts based on word embedding clustering and convolutional neural network (CNN). Empirically, the semantically related words are usually close to each other in embedding spaces. Thus, we first discover semantic cliques via fast clustering. Then, by using additive composition over word embeddings from context with variable window width, the representations of multi-scale semantic units(1) in short texts are computed. In embedding spaces, the restricted nearest word embeddings (NWEs)(2) of the semantic units are chosen to constitute expanded matrices, where the semantic cliques are used as supervision information. Finally, for a short text, the projected matrix(3) and expanded matrices are combined and fed into CNN in parallel. Experimental results on two open benchmarks validate the effectiveness of the proposed method. (C) 2015 Elsevier B.V. All rights reserved.
KeywordShort Text Classification Clustering Convolutional Neural Network Semantic Units Word Embeddings
WOS HeadingsScience & Technology ; Technology
DOI10.1016/j.neucom.2015.09.096
Indexed BySCI
Language英语
Funding OrganizationNational Natural Science Foundation of China(61203281 ; Hundred Talents Program of Chinese Academy of Sciences(Y3S4011D31) ; 61303172 ; 61403385)
WOS Research AreaComputer Science
WOS SubjectComputer Science, Artificial Intelligence
WOS IDWOS:000367276900025
Citation statistics
Cited Times:68[WOS]   [WOS Record]     [Related Records in WOS]
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/10583
Collection数字内容技术与服务研究中心_听觉模型与认知计算
Affiliation1.Chinese Acad Sci, Inst Automat, Beijing 100190, Peoples R China
2.Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
First Author AffilicationInstitute of Automation, Chinese Academy of Sciences
Recommended Citation
GB/T 7714
Wang, Peng,Xu, Bo,Xu, Jiaming,et al. Semantic expansion using word embedding clustering and convolutional neural network for improving short text classification[J]. NEUROCOMPUTING,2016,174:806-814.
APA Wang, Peng,Xu, Bo,Xu, Jiaming,Tian, Guanhua,Liu, Cheng-Lin,&Hao, Hongwei.(2016).Semantic expansion using word embedding clustering and convolutional neural network for improving short text classification.NEUROCOMPUTING,174,806-814.
MLA Wang, Peng,et al."Semantic expansion using word embedding clustering and convolutional neural network for improving short text classification".NEUROCOMPUTING 174(2016):806-814.
Files in This Item: Download All
File Name/Size DocType Version Access License
Neurocomputing-2015.(627KB)期刊论文作者接受稿开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Wang, Peng]'s Articles
[Xu, Bo]'s Articles
[Xu, Jiaming]'s Articles
Baidu academic
Similar articles in Baidu academic
[Wang, Peng]'s Articles
[Xu, Bo]'s Articles
[Xu, Jiaming]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Wang, Peng]'s Articles
[Xu, Bo]'s Articles
[Xu, Jiaming]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: Neurocomputing-2015.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.