MBT2 : 実例に基づく翻訳における複数翻訳例の組合せ利用

概要

論文の詳細を見る
Example-Based Translation is a new approach to machine translation. The basic idea is very simple : translation by using or imitating translation examples. An essential problem of example-based translation is how to utilize more than one translation example for translating one source sentence. This paper proposes MBT2, which is a method to solve this problem. We introduce the representation, called matching expression, which represents the combination of fragments of translation examples. The translation process consists of three steps : (1) Make the source matching expression from the source sentence. (2) Transfer the source matching expression into the target matching expression. (3) Construct the target sentence from the target matching expression. This mechanism generates some translation candidates. To select the best translation from them, we define the score of a translation. We implemented MBT2 in English-Japanese translation.
社団法人人工知能学会の論文
1991-11-01