Chinese Treebanks and Grammar Extraction

Preparation of knowledge bank is a very difficult task. In this paper, we discuss the knowledge extraction from the manually examined Sinica Treebank. Categorical information, word-to-word relation, word collocations, new syntactic patterns and sentence structures are obtained. A searching system for Chinese sentence structure was developed in this study. By using pre-extracted data and SQL com-mands, the system replies the user's que-ries efficiently. We also analyze the extracted grammars to study the tradeoffs between the granularity of the grammar rules and their coverage as well as ambi-guities. It provides the information of knowing how large a treebank is suffi-cient for the purpose of grammar extrac-tion. Finally, we also analyze the tradeoffs between grammar coverage and ambigu-ity by parsing results from the grammar rules of different granularity. Key Words: treebanks, knowledge ex-traction, grammar coverage, ambiguities, parsing.