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
2017
会议名称the 24th International Conference On Neural Information Processing (ICONIP)
会议日期November 14-18, 2017
会议地点Guangzhou, China
摘要Topic 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 https://github.com/njoe9/H-HANs.
关键词Hierarchical Attention Networks Chinese Conversation Topic Classification Recurrent Neural Networks
收录类别EI
语种英语
文献类型会议论文
条目标识符http://ir.ia.ac.cn/handle/173211/15459
专题数字内容技术与服务研究中心_听觉模型与认知计算
通讯作者Li, Changliang
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,Li, Changliang,Xu, Bo,et al. Hierarchical Hybrid Attention Networks for Chinese Conversation Topic 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_(597KB)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
[Li, Changliang]的文章
[Xu, Bo]的文章
百度学术
百度学术中相似的文章
[Zhou, Yujun]的文章
[Li, Changliang]的文章
[Xu, Bo]的文章
必应学术
必应学术中相似的文章
[Zhou, Yujun]的文章
[Li, Changliang]的文章
[Xu, Bo]的文章
相关权益政策
暂无数据
收藏/分享
文件名: 周玉军_201418014629107_H-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。