Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
4973669 | Computer Speech & Language | 2017 | 29 Pages |
Abstract
Recent advances in end-to-end neural machine translation models have achieved promising results on high-resource language pairs such as Enâ Fr and Enâ De. One of the major factor behind these successes is the availability of high quality parallel corpora. We explore two strategies on leveraging abundant amount of monolingual data for neural machine translation. We observe improvements by both combining scores from neural language model trained only on target monolingual data with neural machine translation model and fusing hidden-states of these two models. We obtain up to 2 BLEU improvement over hierarchical and phrase-based baseline on low-resource language pair, Turkishâ English. Our method was initially motivated towards tasks with less parallel data, but we also show that it extends to high resource languages such as Csâ En and Deâ En translation tasks, where we obtain 0.39 and 0.47 BLEU improvements over the neural machine translation baselines, respectively.
Related Topics
Physical Sciences and Engineering
Computer Science
Signal Processing
Authors
Caglar Gulcehre, Orhan Firat, Kelvin Xu, Kyunghyun Cho, Yoshua Bengio,