Word-Sense Disambiguation of Korean Predicates Using Sejong Electronic Dictionary and Unsupervised Learning

The Sejong Electronic (machine-readable) Dictionary, developed by the 21st century Sejong Plan, contains a systematically organized information on Korean words. It helps to solve the problems encountered in the electronic formatting of a still-commonly-used hard-copy dictionary. The Sejong Electronic Dictionary, however, has a limitation relating to sentence structure and selection-restricted nouns. This paper discusses the limitations of word-sense disambiguation (WSD) that proceeds by subcategorization information suggested by the Sejong Electronic Dictionary and generalized selection-restricted nouns of arguments from the Korean Lexico-semantic network. An alternative method that utilizes unsupervised learning, chi-square test and prior probability to make WSD decisions is presented herein.