An Empirical Study of the Impact of Idioms on Phrase Based Statistical Machine Translation of English to Brazilian-Portuguese

摘要

This paper describes an experiment to evaluate the impact of idioms on Statistical Machine Translation (SMT) process using the language pair English/Brazilian-Portuguese. Our results show that on sentences containing idioms a standard SMT system achieves about half the BLEU score of the same system when applied to sentences that do not contain idioms. We also provide a short error analysis and outline our planned work to overcome this limitation.