CASIA OpenIR  > 数字内容技术与服务研究中心  > 听觉模型与认知计算
Hybrid Attention Networks for Chinese Short Text Classification
Zhou, Yujun1,2,3; Xu, Jiaming1; Cao, Jie1,2,3; Xu, Bo1; Li, Changliang1; Xu, Bo1
2017
Conference Namethe 18th International Conference on Computational Linguistics and Intelligent Text Processing (CICLing)
Conference DateApril 17-23, 2017
Conference PlaceBudapest, Hungary
AbstractTo improve the classification performance for Chinese short text with automatic semantic feature selection, in this paper we propose the Hybrid Attention Networks (HANs) which combines the word- and character-level selective attentions. The model firrstly applies RNN and CNN to extract the semantic features of texts. Then it captures class-related attentive representation from word- and character-level features. Finally, all of the features are concatenated and fed into the output layer for classification. Experimental results on 32-class and 5-class datasets show that, our model outperforms multiple baselines by combining not only the word- and character-level features of the texts, but also class-related semantic features by attentive mechanism.
KeywordChinese Short Text Text Classification Attentive Mechanism Convolutional Neural Network Recurrent Neural Network
Indexed By其他
Language英语
Document Type会议论文
Identifierhttp://ir.ia.ac.cn/handle/173211/15617
Collection数字内容技术与服务研究中心_听觉模型与认知计算
Affiliation1.Institute of Automation, Chinese Academy of Sciences
2.University of Chinese Academy of Sciences
3.Jiangsu Jinling Science and Technology Group Co., Ltd, Nanjing
First Author AffilicationInstitute of Automation, Chinese Academy of Sciences
Recommended Citation
GB/T 7714
Zhou, Yujun,Xu, Jiaming,Cao, Jie,et al. Hybrid Attention Networks for Chinese Short Text Classification[C],2017.
Files in This Item: Download All
File Name/Size DocType Version Access License
周玉军_201418014629107_(788KB)会议论文 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
[Zhou, Yujun]'s Articles
[Xu, Jiaming]'s Articles
[Cao, Jie]'s Articles
Baidu academic
Similar articles in Baidu academic
[Zhou, Yujun]'s Articles
[Xu, Jiaming]'s Articles
[Cao, Jie]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Zhou, Yujun]'s Articles
[Xu, Jiaming]'s Articles
[Cao, Jie]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: 周玉军_201418014629107_HANs.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

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