Compositional Recurrent Neural Networks for Chinese Short Text Classification
Zhou, Yujun1,2,3; Xu, Bo1; Xu, Jiaming1; Yang, Lei1,2,3; Li, Changliang1; Xu, Bo1
2016
会议名称the 2016 IEEE/WIC/ACM International Conference on Web Intelligence (WI'16)
会议日期October 13-16, 2016
会议地点Omaha, Nebraska, USA
摘要Word segmentation is the first step in Chinese natural language processing, and the error caused by word segmentation can be transmitted to the whole system. In order to reduce the impact of word segmentation and improve the overall performance of Chinese short text classification system, we propose a hybrid model of character-level and word-level features based on recurrent neural network (RNN) with long short-term memory (LSTM). By integrating character-level feature into word-level feature, the missing semantic information by the error of word segmentation will be constructed, meanwhile the wrong semantic relevance will be reduced. The final feature representation is that it suppressed the error of word segmentation in the case of maintaining most of the semantic features of the sentence.The whole model is finally trained end-to-end with supervised Chinese short text classification task. Results demonstrate that the proposed model in this paper is able to represent Chinese short text effectively, and the performances of 32-class and 5-class categorization outperform some remarkable methods.
关键词Chinese Short Text Text Classification Convolutional Neural Network Recurrent Neural Network Word And Character Embeddings
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/173211/15618
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, Bo,Xu, Jiaming,et al. Compositional Recurrent Neural Networks for Chinese Short Text Classification[C],2016.
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_(354KB)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, Bo]的文章
[Xu, Jiaming]的文章
百度学术
百度学术中相似的文章
[Zhou, Yujun]的文章
[Xu, Bo]的文章
[Xu, Jiaming]的文章
必应学术
必应学术中相似的文章
[Zhou, Yujun]的文章
[Xu, Bo]的文章
[Xu, Jiaming]的文章
相关权益政策
暂无数据
收藏/分享
文件名: 周玉军_201418014629107_C-(B)LSTMs.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。