Semantic Classification of Automatically Acquired Nouns using Lexico-Syntactic Clues

In this paper, we present a two-stage ap-proach to acquire Japanese unknown mor-phemes from text with full POS tags as-signed to them. We first acquire unknown morphemes only making a morphology-level distinction, and then apply semantic classification to acquired nouns. One ad-vantage of this approach is that, at the sec-ond stage, we can exploit syntactic clues in addition to morphological ones because as a result of the first stage acquisition, we can rely on automatic parsing. Japanese semantic classification poses an interest-ing challenge: proper nouns need to be distinguished from common nouns. It is because Japanese has no orthographic distinction between common and proper nouns and no apparent morphosyntactic distinction between them. We explore lexico-syntactic clues that are extracted from automatically parsed text and inves-tigate their effects.