Design and Implementation of the Compound Noun Segmentation Algorithm Based on Statistical Information

This paper suggests a reverse segmentation algorithm using affix information and some preference pattern information of Korean compound nouns. The structure of Korean compound nouns is mostly derived from Chinese characters, and it includes some preference patterns utilized as a segmentation rule in this paper. To evaluate the accuracy of the proposed algorithm, an experiment was performed with 36,061 compound nouns. The experiment resulted in getting 99.3% of correct segmentation and showed excellent satisfactory results from the comparative experimentation with other algorithms. Especially, most of the four-syllable or five-syllable compound nouns were successfully segmented without fail.