Integration of statistical collocation segmentations in a phrase-based statistical machine translation system

Abstract

This study evaluates the impact of integrating two different collocation segmentations methods in a standard phrase-based statistical machine translation approach. The collocation segmentation techniques are implemented simultaneously in the source and target side. Each resulting collocation segmentation is used to extract translation units. Experiments are reported in the English-to-Spanish Bible task and promising results (an improvement over 0.7 BLEU absolute) are achieved in translation quality.