Improving phrase-based statistical translation through combination of word alignments

This paper investigates the combination of word-alignments computed with the competitive linking algorithm and well-established IBM models. New training methods for phrase-based statistical translation are proposed, which have been evaluated on a popular traveling domain task, with English as target language, and Chinese, Japanese, Arabic and Italian as source languages. Experiments were performed with a highly competitive phrase-based translation system, which ranked at the top in the 2005 IWSLT evaluation campaign. By applying the proposed techniques, even under very different data-sparseness conditions, consistent improvements in BLEU and NIST scores were obtained on all considered language pairs.