Jane: Open Source Machine Translation System Combination

Different machine translation engines can be remarkably dissimilar not only with re-spect to their technical paradigm, but also with respect to the translation output they yield. System combination is a method for combining the output of multiple machine translation engines in order to take benefit of the strengths of each of the individual engines. In this work we introduce a novel system combination implementation which is in-tegrated into Jane, RWTH’s open source statistical machine translation toolkit. On the most recent Workshop on Statisti-cal Machine Translation system combi-nation shared task, we achieve improve-ments of up to 0.7 points in BLEU over the best system combination hypotheses which were submitted for the official eval-uation. Moreover, we enhance our sys-tem combination pipeline with additional n-gram language models and lexical trans-lation models.