On the Importance of Pivot Language Selection for Statistical Machine Translation

Recent research on multilingual statistical machine translation focuses on the usage of pivot languages in order to overcome resource limitations for certain language pairs. Due to the richness of available language resources, English is in general the pivot language of choice. In this paper, we investigate the appropriateness of languages other than English as pivot languages. Experimental results using state-of-the-art statistical machine translation techniques to translate between twelve languages revealed that the translation quality of 61 out of 110 language pairs improved when a non-English pivot language was chosen.