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

スポンサーリンク

概要

• 論文の詳細を見る

• This paper descrobes a new method for learing 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 relatively literal translations and (2) more challenging texts: a stock market bulletin in Japanese and its abstract in English. In both cases, domain specific collocations are well captured even if they were not contained in the dictionaries of specialized terms.

• 1998-10-25

著者

• Ikehara Satoru

  Faculty Of Engineering Tottori University

• HARUNO Masahiko

  NTT communication Science Laboratories

関連論文

• A Method of Ordering English Adverbs : as exemplified in Japanese-to-English Machine Translation
• Two-Step Extraction of Bilingual Collocations by Using Word-Level Sorting

スポンサーリンク