基于卷积神经网络的文本分类算法

Text Classification Algorithm Based on Convolution Neural Network

为了解决分类算法在文本分类时出现特征维度过高和数据稀疏的间题,提出了一种基于卷积神经网络(convolutional neural network,CNN)的文本分类算法,该算法结合卷积神经网络论中的邻接矩阵对文本分类进行动态建模。对文本的词向量进行训练,并且通过分类邻接矩阵得到群的结构和个数分类。在提取出文本抽象特征的基础上用CNN分类器来进行分类。仿真分析表明:该算法在在进行文本分类效果显著。

In order to solve the problem of high feature dimension and sparse data,a kind of convolution neural network is proposed to solve the classification algorithm in text classification.（ convolutional neural network,CNN） text classification algorithm,the algorithm combines adjacency matrix convolution neural network theory in the dynamic modeling of text classification. Secondly,the training of word vector the text,and the classification of the adjacency matrix to obtain the group structure and the number of classification. Finally,the extracted text based abstract features with CNN classifier. The simulation results show that the algorithm is effective in the text classification.