Application of Translation Knowledge Acquired by Hierarchical Phrase Alignment for Pattern-based MT
Kenji Imamura · 2002
Hierarchical phrase alignment is a method for extracting equivalent phrases from bilingual sentences, even though they belong to different language families. The method automatically extracts transfer knowledge from about 125K English and Japanese bilingual sentences and then applies it to a pattern-based MT system. The translation quality is then evaluated. The knowledge needs to be cleaned, since the corpus contains various translations and the phrase alignment contains errors. Various cleaning methods are applied in this paper. The results indicate that when the best cleaning method is used, the knowledge acquired by hierarchical phrase alignment is comparable to manually acquired knowledge. 1