Title :
A statistics based method of mining hierarchical word relation
Author :
Xiao, Hu ; Qinyi, Wu ; Yixin, Zhong
Author_Institution :
Pattern Recognition & Intelligence Syst. Res. Center, Beijing Univ. of Posts & Telecommun., China
Abstract :
Proposes an approach to extracting topic words at different levels in any specific domain. The method is based on the statistic features of terms in a large amount of text documents: term frequency and inverse document frequency. Preliminary experiments in Chinese have indicated that the words mined out are basically coincident with the objective reality. So, this approach is helpful for utilizing computers to discover the semantic relationships between words
Keywords :
knowledge acquisition; knowledge representation; text analysis; hierarchical word relation; information mining; inverse document frequency; knowledge representation; statistics based method; term frequency; text documents; text mining; Concrete; Data mining; Feature extraction; Frequency; Intelligent systems; Knowledge acquisition; Natural language processing; Statistics; Text analysis; Text mining;
Conference_Titel :
Info-tech and Info-net, 2001. Proceedings. ICII 2001 - Beijing. 2001 International Conferences on
Conference_Location :
Beijing
Print_ISBN :
0-7803-7010-4
DOI :
10.1109/ICII.2001.983050
