Learning bilingual collocations by word-level sorting

Abstract

This paper proposes a new method for learning bilingual collocations from sentence-aligned parallel corpora. Our method comprises two steps: (1) extracting useful word chunks (n-grams) by word-level sorting and (2) constructing bilingual collocations by combining the word-chunks acquired in stage (1). We apply the method to a very challenging text pair: a stock market bulletin in Japanese and its abstract in English. Domain specific collocations are well captured even if they were not contained in the dictionaries of economic terms.