Bunsetsu Identi cation Using Category-Exclusive Rules

This paper describes two new bunsetsu identi cation methods using supervised learning. Since Japanese syntactic analysis is usually done after bunsetsu identi cation, bunsetsu identi cation is important for analyzing Japanese sentences. In experiments comparing the four previously available machinelearning methods (decision tree, maximum-entropy method, example-based approach and decision list) and two new methods using category-exclusive rules, the new method using the category-exclusive rules with the highest similarity performed best.