中文版 | English

在结果中检索

CASIA OpenIR

浏览/检索结果: 共5条，第1-5条 帮助

已选(0)清除 条数/页：   排序方式：
Chinese Short Text Classification with Mutual-Attention Convolutional Neural Networks 期刊论文
ACM TRANSACTIONS ON ASIAN AND LOW-RESOURCE LANGUAGE INFORMATION PROCESSING, 2020, 卷号: 19, 期号: 5, 页码: 13
作者:  Hao, Ming;  Xu, Bo;  Liang, Jing-Yi;  Zhang, Bo-Wen;  Yin, Xu-Cheng
收藏  |  浏览/下载：160/0  |  提交时间：2021/03/01
Short text classification  word-level and character-level  feature integration  mutual-attention  convolutional neural networks  
Compositional Recurrent Neural Networks for Chinese Short Text Classification 会议论文
, Omaha, Nebraska, USA, October 13-16, 2016
作者:  Zhou, Yujun;  Xu, Bo;  Xu, Jiaming;  Yang, Lei;  Li, Changliang;  Xu, Bo
收藏  |  浏览/下载：37/0  |  提交时间：2020/10/27
Chinese Short Text  Text Classification  Convolutional Neural Network  Recurrent Neural Network  Word And Character Embeddings  
Hybrid Attention Networks for Chinese Short Text Classification 会议论文
, Budapest, Hungary, April 17-23, 2017
作者:  Zhou, Yujun;  Xu, Jiaming;  Cao, Jie;  Xu, Bo;  Li, Changliang;  Xu, Bo
收藏  |  浏览/下载：78/0  |  提交时间：2020/10/27
Chinese Short Text  Text Classification  Attentive Mechanism  Convolutional Neural Network  Recurrent Neural Network  
Semantic expansion using word embedding clustering and convolutional neural network for improving short text classification 期刊论文
NEUROCOMPUTING, 2016, 卷号: 174, 期号: 2016, 页码: 806-814
作者:  Wang, Peng;  Xu, Bo;  Xu, Jiaming;  Tian, Guanhua;  Liu, Cheng-Lin;  Hao, Hongwei
Adobe PDF(1127Kb)  |  收藏  |  浏览/下载：308/103  |  提交时间：2020/10/27
Short Text  Classification  Clustering  Convolutional Neural Network  Semantic Units  Word Embeddings  
Chinese Short Text Classification Based on Domain Knowledge 会议论文
In Proceedings of the 6th International Joint Conference on Natural Language Processing(IJCNLP), pp. 859–863, Nagoya, Japan, 2013-10-14
作者:  Xiao Feng;  Yang Shen;  Chengyong Liu;  Wei Liang;  Shuwu Zhang
Adobe PDF(248Kb)  |  收藏  |  浏览/下载：406/119  |  提交时间：2016/05/04
Text Classification  Short Text  Domain Knowledge