Dependency-Based Decipherment for Resource-Limited Machine Translation

We introduce dependency relations into deci-phering foreign languages and show that de-pendency relations help improve the state-of-the-art deciphering accuracy by over 500%. We learn a translation lexicon from large amounts of genuinely non parallel data with decipherment to improve a phrase-based ma-chine translation system trained with limited parallel data. In experiments, we observe BLEU gains of 1.2 to 1.8 across three different test sets. 1