摘要
论述了网页文档带权语言网络的建立过程,给出了结合介数指标与紧密度指标的词语综合中心度度量方法,实验表明采用该方法的关键词抽取结果能够很好地符合网页主题。
Building weighted natural language network for the Web page is introduced in the paper,and the centrality of word combines the betweenness metric and the closeness metric.Experiments show that the words extracted have great contribution to the Web page subject.
出处
《计算机工程与应用》
CSCD
北大核心
2008年第8期155-157,共3页
Computer Engineering and Applications
关键词
网页
语言网络
关键词抽取
中心度
Web page
natural language network
keywords extraction
centrality
