Deciphering Foreign Language

Sujith Ravi and Kevin Knight
USC Information Sciences Institute


Abstract

In this work, we tackle the task of machine translation (MT) without parallel training data. We frame the MT problem as a decipherment task, treating the foreign text as a cipher for English and present novel methods for training translation models from non-parallel text.




Full paper: http://www.aclweb.org/anthology/P/P11/P11-1002.pdf