An Unsupervised Method for Canonicalization of Japanese Postpositions

We present an unsupervised method for canonicalizing joshi (postpositions) in Japanese. Some postpositions in Japanese do not specify semantic roles explicitly as case markers do, although those postpositions syntactically behave as the case markers. Such postpositions includes “wa,” which topicalizes noun phrases, and “mo,” which emphasizes noun phrases. For this paper, we replaced these postpositions in a sentence with case markers, without changing the meanings of the original sentence as little as possible. This leads to canonicalization or paraphrasing of verb phrases into canonical forms with desirable properties. Our method utilized case frames and semantic word classifications induced by the Expectation Maximization algorithm. The induction process was unsupervised in the sense that no semantic clues were given before the induction of the case frames and the word classifications.

• Type: Conference
• Year: 2001
• Where: NLPRS
• Authors: Kentaro Torisawa
• Keywords: Case Frames, Case Markers, Natural Language Processing, NLPRS 2001, Noun Phrases