Statistical Matching of Two Ontologies
Satoshi Sekine, Kiyoshi Sudo, Takano Ogino · 1999
Introduction 'Standard,zing ontologles xs a challenging task Ontologles have been created based on different backgrounds, different purposes and d,fferent people However, standardizing them m useful not only for apphcatmns, such as Machine Translation and Informat,on Retrieval, but also to improve the. ontologles themselves During the process of standardlzat, on, people can find bugs or gaps m onrologins So standardization brings benefits compared to just umng them separately There ,s a committee for standardrang ontologues at ANSI, the "ANSI Ad-Hoc Group for Ontology Standards " (Hovy 1996) Although there have been a few attempts to merge and compare ontologues, thin work m still at a prehmmary stage of research (Oglno et al 1997) attempts manual merging of EDR (EDR 1996) (Mlyosh, et al 1996) and WordNet (Wordnet) (Mfiler 1995), (Utlyama and Hashida 1997) used statlst,cal methods to merge EDR and WordNet (Pangloss) is also working on standard,zing ontologms It ,s certain that manual