‘단어-의미 의미-단어’ 관계에 기반한 번역어 선택

Abstract

To obtain a correctly translated sentence in a machine translation system, we must select target words that not only reflect an appropriate meaning in a source sentence but also make a fluent sentence in a target language. This paper points out that a source language word has various senses and each sense can be mapped into multiple target words, and proposes a new translation disambiguation method based on this ‘word-to-sense and sense-to-word’ relationship. In my method, target words are chosen through disambiguation of a source word sense and selection of a target word. Most of translation disambiguation methods are based on a ‘word-to-word’ relationship that means they translate a source word directly into a target word, so they require complicate knowledge sources that directly link a source words to target words, which are hard to obtain like bilingual aligned corpora. By combining two sub-problems for each language, knowledge for translation disambiguation can be automatically extracted from knowledge sources for each language that are easy to obtain. In addition, disambiguation results satisfy both fidelity and intelligibility because selected target words have correct meaning and generate naturally composed target sentences.