A Nearly Unsupervised Learning Method for Automatic Paraphrasing of Japanese Noun Phrases

This paper describes a nealy unsupervised learning method for converting or paraphrasing Japanese noun phrases to verb phrases without changing their semantic contents. We focus on the paraphrasing of the noun phrases in the form of “A no B” where “A” and “B” are noun phrases and “no” is a postposition. Noun phrases in this form can express various relationships between “A” and “B.” In the past, semantic analyses of the noun phrases were performed by choosing up a relation from a relatively small set of pre-defined semantic relations. However, some researchers pointed out that “no” can denote a broad range of relationships that can be expressed only by introducing various verbs. For instance, the noun phrase “restaurant no beer” can be paraphrased to the relative clause “the beer that someone drinks at a restaurant.” The relationship between “restaurant” and “beer” cannot be expressed without introducing the verb “drink.” We sought to perform this type of paraphrasing without manually tailored dictionaries and thesauri. Instead, we use the semantic case frames and word classifications obtained by an unsupervised statistical learning method.