基于CNN和LSTM混合模型的中文新闻文本分类  

Text Classification of Chinese News Based on CNN and LSTM Hybrid Model

作　　者：张欣 翟正利 姚路遥 ZHANG Xin;ZHAI Zhengi;YAO Luyao(School of Information and Control Engineering,Qingdao University of Technology,Qingdao 266000)

机构地区：[1]青岛理工大学信息与控制工程学院,青岛266000

出　　处：《计算机与数字工程》2023年第7期1540-1543,1573,共5页Computer & Digital Engineering

摘　　要：论文结合了卷积神经网络(CNN)和递归神经网络(RNN)的优点,提出了一种CNN和LSTM的混合模型。首先,使用CNN获取文本句子的特征,并使用LSTM模型捕捉文本上下文的依赖关系。然后将这两部分生成的特征向量进行融合,形成一个新的特征向量,它兼有CNN和LSTM的优点。最后,采用softmax层进行最终分类。In this paper,a hybrid model of CNN and LSTM is proposed by combining the advantages of convolutional neural network(CNN)and recurrent neural network(RNN).First of all,CNN is used to obtain the features of text sentences,and LSTM model is used to capture the dependency of text context.Then the feature vectors generated by these two parts are fused to form a new feature vector,which has the advantages of both CNN and LSTM.Finally,softmax layer is used for final classification.

关 键 词：自然语言处理 文本分类 神经网络 卷积 长短时记忆 

分 类 号：TP391.1[自动化与计算机技术—计算机应用技术]