Munich-Edinburgh-Stuttgart Submissions of OSM Systems at WMT13

This paper describes Munich-EdinburghStuttgart’s submissions to the Eighth Workshop on Statistical Machine Translation. We report results of the translation tasks from German, Spanish, Czech and Russian into English and from English to German, Spanish, Czech, French and Russian. The systems described in this paper use OSM (Operation Sequence Model). We explain different pre-/post-processing steps that we carried out for different language pairs. For German-English we used constituent parsing for reordering and compound splitting as preprocessing steps. For Russian-English we transliterated the unknown words. The transliteration system is learned with the help of an unsupervised transliteration mining algorithm.