Expansion of Feature Information for Korean Semantic Role Labeling

Semantic role labeling is defined as determination of the semantic relation between a predicate and various arguments that are dependent on the given predicate. In this study, automatic semantic role labeling using 10,000 sentences in a semantic role tagged corpus constructed from a Korean syntax tagged corpus was conducted. In the Korean language, the grammatical relation between particle and word ending as well as their semantic relation is very important. When features based on the affix information created in this study were added to the basic features used in previous studies on semantic role labeling of languages, an F1 score of approximately 80.83% was obtained.