Corpus-based generation of numeral classifier using phrase alignment

要旨

A severe problem for NLP applications dealing with multilingual language resources is the acquisition of knowledge that is obligatory in one language but not explicitly expressed in another language. In this paper, we focus on numeral classifiers, which are required in languages like Japanese but are usually not explicitly used in languages like English, which don't have such a classifier system.We propose a uniform method to assign the numeral classifiers of languages that have a numeral classifier system to the numerals of non-classifier languages. The omitted classifier information is extracted from a bilingual corpus based on phrasal correspondences in the contexts of the respective sentences.

主題