Paraphrasing swedish compound nouns in machine translation

Abstract

This paper examines the effect of paraphrasing noun-noun compounds in statistical machine translation from Swedish to English. The paraphrases are meant to elicit the underlying relationship that holds between the compounding nouns, with the use of prepositional and verb phrases. Though some types of noun-noun compounds are too lexicalized, or have some other qualities that make them unsuitable for paraphrasing, a set of roughly two hundred noun-noun compounds are identified, split and paraphrased to be used in experiments on statistical machine translation. The results indicate a slight improvement in translation of the paraphrased compound nouns, with a minor loss in overall BLEU score.