Conference Proceedings
Corpus-based extraction of Japanese compound verbs
J Breen, T Baldwin
Australasian Language Technology Association Workshop Alta 2009 Proceedings | Australasian Language Technology Association | Published : 2009
Abstract
We describe two methods for Japanese compound verb (JCV) extraction, based on synthesis and pattern matching over the Google Japanese n-gram corpus. We devise a number of filters to boost the precision of the corpus-based method, and evaluate the two methods based on a sample of JCVs occurring in varying frequency bands. We also investigate the distribution of JCV token frequency, and the type frequency of their components.