A Novel Document Analysis Method Using Compressibility Vector
Nuo Zhang, Toshinori Watanabe, Daisuke Matsuzaki, Hisashi Koga · 2007
Similarity analysis and keyword extraction are widely used as document relation analysis techniques. These meth- ods are based on dictionary-base morphological analysis. However, they cannot meet the need when Internet grows fast and new words appear but dictionary can not be re- newed fast enough. In this study, we propose a new doc- ument relation analysis method based on the document's compressibility. The effectiveness of the proposed method will be examined in simulations.