CASIA OpenIR  > 数字内容技术与服务研究中心  > 听觉模型与认知计算
Hierarchical Hybrid Attention Networks for Chinese Conversation Topic Classification
Zhou, Yujun1,2,3; Li, Changliang1; Xu, Bo1; Xu, Jiaming1; Cao, Jie1,2,3; Xu, Bo1
Conference Namethe 24th International Conference On Neural Information Processing (ICONIP)
Conference DateNovember 14-18, 2017
Conference PlaceGuangzhou, China
AbstractTopic classification is useful for applications such as forensics analysis and cyber-crime investigation. To improve the overall performance on the task of Chinese conversation topic classi cation, we propose a hierarchical neural network with automatic semantic features selection, which is a hierarchical architecture that depicts the structure of conversations. The model firstly incorporates speaker information into the character- and word-level attentions and generates sentence representation, then uses attention-based BLSTM to construct the conversation representation. Experimental results on three datasets demonstrate that our model achieves better performance than multiple baselines. It indicates that the proposed architecture can capture the informative and salient features related to the meaning of a conversation for topic classification. And we release the dataset of this paper that can be obtained from
KeywordHierarchical Attention Networks Chinese Conversation Topic Classification Recurrent Neural Networks
Indexed ByEI
Document Type会议论文
Corresponding AuthorLi, Changliang
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
Recommended Citation
GB/T 7714
Zhou, Yujun,Li, Changliang,Xu, Bo,et al. Hierarchical Hybrid Attention Networks for Chinese Conversation Topic Classification[C],2017.
Files in This Item: Download All
File Name/Size DocType Version Access License
周玉军_201418014629107_(597KB)会议论文 开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Zhou, Yujun]'s Articles
[Li, Changliang]'s Articles
[Xu, Bo]'s Articles
Baidu academic
Similar articles in Baidu academic
[Zhou, Yujun]'s Articles
[Li, Changliang]'s Articles
[Xu, Bo]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Zhou, Yujun]'s Articles
[Li, Changliang]'s Articles
[Xu, Bo]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: 周玉军_201418014629107_H-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.