The TaxGen framework: automating the generation of a taxonomy for alarge document collection

摘要

Text mining is an active area of research and development, whichcombines and expands techniques found in related areas like informationretrieval, computational linguistics and data mining to perform ananalysis of large corpora of digital documents. This paper describes theTaxGen text mining project carried out at the IBM Software DevelopmentLab. at Boeblingen, Germany. The goal of TaxGen was the automaticgeneration of a taxonomy for a collection of previously unstructureddocuments, namely a set of 73,000 news wire documents spanning one year