Fusion of heterogeneous attention mechanisms in multi-view convolutional neural network for text classification | |
Liang, Yunji2; Li, Huihui2; Guo, Bin2; Yu, Zhiwen2; Zheng, Xiaolong2,3,4; Samtani, Sagar1; Zeng, Daniel D.3,4 | |
刊名 | INFORMATION SCIENCES |
2021-02-16 | |
卷号 | 548页码:295-312 |
关键词 | View attention Spatial attention Multi-view representation Series and parallel connection Conventional neural network Text classification |
ISSN号 | 0020-0255 |
DOI | 10.1016/j.ins.2020.10.021 |
通讯作者 | Liang, Yunji(liangyunji@nwpu.edu.cn) ; Zheng, Xiaolong(xiaolong.zheng@ia.ac.cn) |
英文摘要 | The rapid proliferation of user generated content has given rise to large volumes of text corpora. Increasingly, scholars, researchers, and organizations employ text classification to mine novel insights for high-impact applications. Despite their prevalence, conventional text classification methods rely on labor-intensive feature engineering efforts that are task specific, omit long-term relationships, and are not suitable for the rapidly evolving domains. While an increasing body of deep learning and attention mechanism literature aim to address these issues, extant methods often represent text as a single view and omit multiple sets of features at varying levels of granularity. Recognizing that these issues often result in performance degradations, we propose a novel Spatial View Attention Convolutional Neural Network (SVA-CNN). SVA-CNN leverages an innovative and carefully designed set of multi-view representation learning, a combination of heterogeneous attention mechanisms and CNN-based operations to automatically extract and weight multiple granularities and fine-grained representations. Rigorously evaluating SVA-CNN against prevailing text classification methods on five large-scale benchmark datasets indicates its ability to outperform extant deep learning based classification methods in both performance and training time for document classification, sentiment analysis, and thematic identification applications. To facilitate model reproducibility and extensions, SVA-CNN's source code is also available via GitHub. (c) 2020 Elsevier Inc. All rights reserved. |
资助项目 | National Key Research and Development Program of China[2019YFB2102200] ; ministry of health of China[2017ZX10303401-002] ; ministry of health of China[2017YFC1200302] ; natural science foundation of China[61902320] ; natural science foundation of China[71472175] ; natural science foundation of China[71602184] ; natural science foundation of China[71621002] ; national science foundation[CNS-1850362] ; national science foundation[OAC-1917117] ; fundamental research funds for the central universities[31020180QD140] |
WOS研究方向 | Computer Science |
语种 | 英语 |
出版者 | ELSEVIER SCIENCE INC |
WOS记录号 | WOS:000596057300017 |
资助机构 | National Key Research and Development Program of China ; ministry of health of China ; natural science foundation of China ; national science foundation ; fundamental research funds for the central universities |
内容类型 | 期刊论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/42817] |
专题 | 自动化研究所_复杂系统管理与控制国家重点实验室_互联网大数据与安全信息学研究中心 |
通讯作者 | Liang, Yunji; Zheng, Xiaolong |
作者单位 | 1.Indiana Univ, Kelley Sch Business, Operat & Decis Technol Dept, Bloomington, IN 47405 USA 2.Northwestern Polytech Univ, Sch Comp Sci, Xian, Shaanxi, Peoples R China 3.Univ Chinese Acad Sci, Beijing, Peoples R China 4.Chinese Acad Sci, State Key Lab Management & Control Complex Syst, Inst Automat, Beijing, Peoples R China |
推荐引用方式 GB/T 7714 | Liang, Yunji,Li, Huihui,Guo, Bin,et al. Fusion of heterogeneous attention mechanisms in multi-view convolutional neural network for text classification[J]. INFORMATION SCIENCES,2021,548:295-312. |
APA | Liang, Yunji.,Li, Huihui.,Guo, Bin.,Yu, Zhiwen.,Zheng, Xiaolong.,...&Zeng, Daniel D..(2021).Fusion of heterogeneous attention mechanisms in multi-view convolutional neural network for text classification.INFORMATION SCIENCES,548,295-312. |
MLA | Liang, Yunji,et al."Fusion of heterogeneous attention mechanisms in multi-view convolutional neural network for text classification".INFORMATION SCIENCES 548(2021):295-312. |
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