Online learning approaches in Computer Assisted Translation

We present a novel online learning approach for statistical machine translation tailored to the computer assisted translation scenario. With the introduction of a simple online feature, we are able to adapt the translation model on the fly to the corrections made by the translators. Additionally, we do online adaption of the feature weights with a large margin algorithm. Our results show that our online adaptation technique outperforms the static phrase based statistical machine translation system by 6 BLEU points absolute, and a standard incremental adaptation approach by 2 BLEU points absolute.