Name
Abstract | ||
|---|---|---|
Neural Machine Translation (NMT) is a new approach to machine translation that has shown promising results that are comparable to traditional approaches. A significant weakness in conventional NMT systems is their inability to correctly translate very rare words: end-to-end NMTs tend to have relatively small vocabularies with a single unk symbol that represents every possible out-of-vocabulary (OOV) word. In this paper, we propose and implement an effective technique to address this problem. We train an NMT system on data that is augmented by the output of a word alignment algorithm, allowing the NMT system to emit, for each OOV word in the target sentence, the position of its corresponding word in the source sentence. This information is later utilized in a post-processing step that translates every OOV word using a dictionary. Our experiments on the WMT' 14 English to French translation task show that this method provides a substantial improvement of up to 2.8 BLEU points over an equivalent NMT system that does not use this technique. With 37.5 BLEU points, our NMT system is the first to surpass the best result achieved on a WMT' 14 contest task. |
Year | Venue | DocType |
|---|---|---|
2015 | PROCEEDINGS OF THE 53RD ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS AND THE 7TH INTERNATIONAL JOINT CONFERENCE ON NATURAL LANGUAGE PROCESSING, VOL 1 | Conference |
Citations | PageRank | References |
162 | 9.92 | 15 |
Authors | ||
5 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Minh-Thang Luong | 1 | 1852 | 71.35 |
| Ilya Sutskever | 2 | 25814 | 1120.24 |
| Quoc V. Le | 3 | 8501 | 366.59 |
| Oriol Vinyals | 4 | 9419 | 418.45 |
| Wojciech Zaremba | 5 | 2733 | 117.55 |