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
会议名称the 18th International Conference on Computational Linguistics and Intelligent Text Processing (CICLing)
会议日期April 17-23, 2017
会议地点Budapest, Hungary
摘要To 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.
关键词Chinese Short Text Text Classification Attentive Mechanism Convolutional Neural Network Recurrent Neural Network
收录类别其他
语种英语
文献类型会议论文
条目标识符http://ir.ia.ac.cn/handle/173211/15617
专题数字内容技术与服务研究中心_听觉模型与认知计算
作者单位1.Institute of Automation, Chinese Academy of Sciences
2.University of Chinese Academy of Sciences
3.Jiangsu Jinling Science and Technology Group Co., Ltd, Nanjing
推荐引用方式
GB/T 7714
Zhou, Yujun,Xu, Jiaming,Cao, Jie,et al. Hybrid Attention Networks for Chinese Short Text Classification[C],2017.
条目包含的文件 下载所有文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
周玉军_201418014629107_(788KB)会议论文 开放获取CC BY-NC-SA浏览 下载
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Zhou, Yujun]的文章
[Xu, Jiaming]的文章
[Cao, Jie]的文章
百度学术
百度学术中相似的文章
[Zhou, Yujun]的文章
[Xu, Jiaming]的文章
[Cao, Jie]的文章
必应学术
必应学术中相似的文章
[Zhou, Yujun]的文章
[Xu, Jiaming]的文章
[Cao, Jie]的文章
相关权益政策
暂无数据
收藏/分享
文件名: 周玉军_201418014629107_HANs.pdf
格式: Adobe PDF
所有评论 (0)
暂无评论
 

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。