Paper: Beyond Parallel Data: Joint Word Alignment and Decipherment Improves Machine Translation

ACL ID D14-1061
Title Beyond Parallel Data: Joint Word Alignment and Decipherment Improves Machine Translation
Venue Conference on Empirical Methods in Natural Language Processing
Session Main Conference
Year 2014
Authors

Inspired by previous work, where decipher- ment is used to improve machine translation, we propose a new idea to combine word align- ment and decipherment into a single learning process. We use EM to estimate the model pa- rameters, not only to maximize the probabil- ity of parallel corpus, but also the monolingual corpus. We apply our approach to improve Malagasy-English machine translation, where only a small amount of parallel data is avail- able. In our experiments, we observe gains of 0.9 to 2.1 Bleu over a strong baseline.