Improving Word Alignment Through Morphological Analysis

Word alignment plays a critical role in statistical machine translation systems. The famous word alignment system, IBM models series, currently operates on only surface forms of words regardless of their linguistic features. This deficiency usually leads to many data sparseness problems. Therefore, we present an extension that enables the integration of morphological analysis into the traditional IBM models. Experiments on English-Vietnamese tasks show that the new model produces better results not only in word alignment but also in final translation performance.