Study on Association Rules Mining Based Chinese Text Representation
In this paper,the problem of text representation in the process of text mining is mainly discussed.The paper focuses on how to simplify the text model in advance of the construction of term-by-document matrix.By using association rules mining method to find the highly correlative words to form words-set,the vocabulary set is decreased effectively,which leads to the text model’s simplification directly.During this process,some incremental update problems of text representation are also introduced.In the end,a simulation case validate that the method is not only efficient but also helpful to the further text clustering.
Fang Li Qunxiong Zhu
School of Computer Science and technology,Beijing University of Chemical Technology,Beijing,China
国际会议
武汉
英文
2008-11-01（万方平台首次上网日期，不代表论文的发表时间）