Japanese Case Frame Construction by Coupling the Verb and its Closest Case Component

Japanese Case Frame Construction by Coupling the Verb and its Closest Case Component Daisuke Kawahara Graduate School of Informatics, Kyoto University Yoshida-Honmachi, Sakyo-ku, Kyoto, 606-8501, Japan kawahara@pine.kuee.kyoto-u.ac.jp Sadao Kurohashi Graduate School of Informatics, Kyoto University Yoshida-Honmachi, Sakyo-ku, Kyoto, 606-8501, Japan kuro@pine.kuee.kyoto-u.ac.jp ABSTRACT This paper describes a method to construct a case frame dic- tionary automatically from a raw corpus. The main prob- lem is how to handle the diversity of verb usages. We col- lect predicate-argument examples, which are distinguished by the verb and its closest case component in order to deal with verb usages, from parsed results of a corpus. Since these couples multiply to millions of combinations, it is dif- ficult to make a wide-coverage case frame dictionary from a small corpus like an analyzed corpus. We, however, use a raw corpus, so that this problem can be addressed. Further- more, we cluster and merge predicate-argument examples which does not have different usages but belong to different case frames because of different closest case components. We also report on an experimental result of case structure analysis using the constructed case frame dictionary. 1. INTRODUCTION Syntactic analysis or parsing has been a main objective in Natural Language Processing. In case of Japanese, however, syntactic analysis cannot clarify relations between words in sentences because of several troublesome characteristics of Japanese such as scrambling, omission of case components, and disappearance of case markers. Therefore, in Japanese sentence analysis, case structure analysis is an important issue, and a case frame dictionary is necessary for the anal- ysis. Some research institutes have constructed Japanese case frame dictionaries manually [2, 3]. However, it is quite ex- pensive, or almost impossible to construct a wide-coverage case frame dictionary by hand. Others have tried to construct a case frame dictionary automatically from analyzed corpora. However, existing syntactically analyzed corpora are too small to learn a dic- tionary, since case frame information consists of relations between nouns and verbs, which multiplies to millions of combinations. Based on such a consideration, we took the unsupervised learning strategy to Japanese case frame con- struction1. To construct a case frame dictionary from a raw corpus, we parse a raw corpus first, but parse errors are problematic in this case. However, if we use only reliable modifier-head relations to construct a case frame dictionary, this problem can be addressed. Verb sense ambiguity is rather problem- atic. Since verbs can have different cases and case compo- nents depending on their meanings, verbs which have dif- ferent meanings should have different case frames. To deal with this problem, we collect predicate-argument examples, which are distinguished by the verb and its closest case com- ponent, and cluster them. That is, examples are not distin- guished by verbs such as naru ‘make, become’ and tsumu ‘load, accumulate’, but by couples such as tomodachi ni naru ‘make a friend’, byouki ni naru ‘become sick’,nimotsu wo tsumu ‘load baggage’, and keiken wo tsumu ‘accumulate experience’. Since these couples multiply to millions of com- binations, it is difficult …

Content truncated to 500 words