Minimum Bayes Risk Combination of Translation Hypotheses from Alternative Morphological Decompositions

We describe a simple strategy to achieve translation performance improvements by combining output from identical statistical machine translation systems trained on alternative morphological decompositions of the source language. Combination is done by means of Minimum Bayes Risk decoding over a shared Nbest list. When translating into English from two highly inflected languages such as Arabic and Finnish we obtain significant improvements over simply selecting the best morphological decomposition.