一种基于BP神经网络的关键词抽取方法  

A keyword extraction method based on BP neural network

作　　者：白晓雷[1] 黄广君[1] 段建辉[1] 

机构地区：[1]河南科技大学信息工程学院,河南洛阳471003

出　　处：《合肥工业大学学报（自然科学版）》2014年第7期808-811,896,共5页Journal of Hefei University of Technology：Natural Science

基　　金：河南省科技攻关计划资助项目(102102210159)

摘　　要：为了进一步提高Web信息抽取的准确性和效率,通过分析传统中文关键词抽取方法,文章提出了一种基于BP神经网络的中文关键词抽取方法。该方法在分析和提取术语特征的基础上,给出了确定网络隐层节点数的表达式和多个术语特征表达式,以此确定网络参数,实现中文关键词的抽取。实验结果表明,该方法查全率、查准率和查找性能较高,具备较好的应用前景。In order to further enhance the accuracy and efficiency of Web information extraction ,a Chinese keyword extraction method based on back propagation（BP） neural network is proposed by analyzing of the traditional Chinese keyword extraction method .The network hidden layer nodes expressions and terminology characteristic expression are given on the basis of analyzing and extracting term characteristic so as to determine the network parameters and achieve the Chinese keyword extraction . The experimental results show that the proposed method possesses high recall ratio ,precision ratio and look-up performance ,and it has a good application prospect .

关 键 词：BP神经网络 抽取 术语特征 网络隐层节点 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]