Hybrid Attention Networks for Chinese Short Text Classification

CORC > 自动化研究所 > 中国科学院自动化研究所 > 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, Jie 1,2,3; Xu, Bo1 ; Li, Changliang1 ; Xu, Bo 1
	2017
会议日期	April 17-23, 2017
会议地点	Budapest, Hungary
关键词	Chinese Short Text Text Classification Attentive Mechanism Convolutional Neural Network Recurrent Neural Network
英文摘要	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.
语种	英语
内容类型	会议论文
源URL	[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]. 见:. Budapest, Hungary. April 17-23, 2017.