Beyond Parallel Data: Joint Word Alignment and Decipherment Improves Machine Translation
Qing Doua b c, Ashish Vaswania b c, Kevin K. Knighta b c
- aDepartment of Computer Science University of Southern California
- bInformation Sciences Institute
- cInformation Sciences Institute Department of Computer Science University of Southern California
Papers open inside SciRah from the original publisher or repository; SciRah never hosts them.
Abstract
Inspired by previous work, where decipherment is used to improve machine translation, we propose a new idea to combine word alignment and decipherment into a single learning process.We use EM to estimate the model parameters, not only to maximize the probability 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 available.In our experiments, we observe gains of 0.9 to 2.1 Bleu over a strong baseline.
TL;DRThis work uses EM to estimate the model parameters, not only to maximize the probability of parallel corpus, but also the monolingual corpus, and applies this approach to improve Malagasy-English machine translation, where only a small amount of parallel data is available. (Semantic Scholar)