Paper: Dependency-Based Decipherment for Resource-Limited Machine Translation

ACL ID D13-1173
Title Dependency-Based Decipherment for Resource-Limited Machine Translation
Venue Conference on Empirical Methods in Natural Language Processing
Session Main Conference
Year 2013
Authors

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.