Korean Combinatory Categorial Grammar and Statistical Parsing.

Korean Combinatory Categorial Grammar (KCCG) is an extended combinatory categorial grammar formalism to capture the syntax and interpretation of a ``relative free'' word order, long distance scrambling, and other specific characteristics of Korean. KCCG formalism can uniformly handle word order variations among arguments and adjuncts within a clause, as well as in complex clauses and across clause boundaries, i.e. long distance scrambling. The approach we develop takes advantage of the ability of CCG for type raising and composition along with the ability of variable categories and unordered argument modeling for relatively free word order treatment (Lee et al., 1994; Lee et al., 1997). We apply a probability model and heuristics using Korean characteristics to our KCCG parser. Results of the experiments on various text genre show that the KCCG parser performs at 87.67/87.03% constituent precision/recall. [ABSTRACT FROM AUTHOR]