The Sejong Electronic(Machine Readable) Dictionary, which was developed by the 21century Sejong Plan, contains a systematic of immanence information of Korean words. It helps in solving the problem of electronical presentation of a general text dictio... The Sejong Electronic(Machine Readable) Dictionary, which was developed by the 21century Sejong Plan, contains a systematic of immanence information of Korean words. It helps in solving the problem of electronical presentation of a general text dictionary commonly used. Word sense disambiguation problems can also be solved using specific information available in the Sejong Electronic Dictionary. However, the Sejong Electronic Dictionary has a limitation of suggesting structure of sentence and selection-restricted nouns. This discusses about limitations of word sense disambiguation by using subcategorization information as suggested by the Sejong Electronic Dictionary and generalize selection-restricted noun of argument using Korean Lexico-semantic network. After that, several sentences that cannot make dicision of word sense using Sejong Electronic Dictionary’s subcategorization information. In this case, some statistical methods will be used to disambiguate word senses. This treats unsupervised learning and chi-square test to make tagged corpus and evaluate correlation between target words of sense disambiguation and their context words. If they have correlation, selection-restricted nouns will be extended using Korean Lexico-semantic network. Finally, the remain sentences that cannot make dicision about word sense will be judged by using prior probability of word sense. ，韩语毕业论文，韩语毕业论文 |
