Two-Step Extraction of Bilingual Collocations by Using Word-Level Sorting

摘要

This paper describes a new method for learn- ing bilingual collocations from sentence-aligned parallel corpora. Our method comprises two steps: (1) extracting useful word chunks (n-grams) in each language by word-level sorting and (2) constructing bilingual collocations by combining the word- chunks acquired in stage(1). We apply the method to a two kinds of Japanese-English texts; (1) scientific articles that comprise rel- atively literal translations and (2) more challenging texts: a stock market bulletin in Japanese and its abstract in English.