Constructing a Practical Constituent Parser from a Japanese Treebank with Function Labels

We present an empirical study on construct-ing a Japanese constituent parser, which can output function labels to deal with more de-tailed syntactic information. Japanese syn-tactic parse trees are usually represented as unlabeled dependency structure between bun-setsu chunks, however, such expression is in-sufficient to uncover the syntactic information about distinction between complements and adjuncts and coordination structure, which is required for practical applications such as syn-tactic reordering of machine translation. We describe a preliminary effort on constructing a Japanese constituent parser by a Penn Tree-bank style treebank semi-automatically made from a dependency-based corpus. The eval-uations show the parser trained on the tree-bank has comparable bracketing accuracy as conventional bunsetsu-based parsers, and can output such function labels as the grammatical role of the argument and the type of adnominal phrases.