Statistical Phrase-based Machine Translation: Experiments with Brazilian Portuguese

Statistical approaches have recently emerged as the main paradigm in Machine Translation (MT) research. In previous work we have shown that results of a simple statistical word-based MT system may be highly comparable to those produced by a rule-based approach for closely-related languages such as Brazilian Portuguese and European Spanish. In this work we take the discussion one step further and present evidence that a more sophisticated (namely, phrase-based) translation model may outperform rulebased translation for this language pair, and additional results of a first experiment in Portuguese/English phrase-based statistical MT.