版权说明 操作指南
首页 > 成果 > 详情

A Hybrid Deep Learning Model for Text Classification

认领
导出
下载 Link by DOI
反馈
分享
QQ微信 微博
成果类型:
会议论文
作者:
Chen, Xianglong;Ouyang, Chunping*;Liu, Yongbin;Luo, Lingyun;Yang, Xiaohua
通讯作者:
Ouyang, Chunping
作者机构:
[Ouyang, Chunping; Yang, Xiaohua; Chen, Xianglong; Liu, Yongbin; Luo, Lingyun] Univ South China, Sch Comp Sci & Technol, Hengyang 421001, Peoples R China.
通讯机构:
[Ouyang, Chunping] U
Univ South China, Sch Comp Sci & Technol, Hengyang 421001, Peoples R China.
语种:
英文
关键词:
Text classification;Deep learning;CNN;RNN
期刊:
2018 14TH INTERNATIONAL CONFERENCE ON SEMANTICS, KNOWLEDGE AND GRIDS (SKG)
ISSN:
2325-0623
年:
2018
页码:
46-52
会议名称:
14th International Conference on Semantics, Knowledge and Grids (SKG)
会议论文集名称:
International Conference on Semantics Knowledge and Grids
会议时间:
SEP 12-14, 2018
会议地点:
Guangzhou, PEOPLES R CHINA
会议主办单位:
[Chen, Xianglong;Ouyang, Chunping;Liu, Yongbin;Luo, Lingyun;Yang, Xiaohua] Univ South China, Sch Comp Sci & Technol, Hengyang 421001, Peoples R China.
会议赞助商:
Guangzhou Univ, Chinese Acad Sci, Chinese Acad Sci, Inst Comp Technol, Natl Basic Res Program China
出版地:
345 E 47TH ST, NEW YORK, NY 10017 USA
出版者:
IEEE
ISBN:
978-1-7281-0441-6
基金类别:
National Natural Science Foundation of ChinaNational Natural Science Foundation of China (NSFC) [61402220, 61502221]; Philosophy and Social Science Foundation of Hunan Province [16YBA323, 14YBA335, 2017SYL16]
机构署名:
本校为第一且通讯机构
院系归属:
计算机科学与技术学院
摘要:
Deep learning has shown its effectiveness in many tasks such as text classification and computer vision. Most text classification tasks are concentrated in the use of convolution neural network and recurrent neural network to obtain text feature representation. In some researches, Attention mechanism is usually adopted to improve classification accuracy. According to the target of task 6 in NLP&CC2018, a hybrid deep learning model which combined BiGRU, CNN and Attention mechanism was proposed to improve text classification. The experimental results show that the Fl-score of the proposed model ...

反馈

验证码:
看不清楚,换一个
确定
取消

成果认领

标题:
用户 作者 通讯作者
请选择
请选择
确定
取消

提示

该栏目需要登录且有访问权限才可以访问

如果您有访问权限,请直接 登录访问

如果您没有访问权限,请联系管理员申请开通

管理员联系邮箱:yun@hnwdkj.com