Abstract | ||
---|---|---|
In machine translation (MT) that involves translating between two languages with significant differences in word order, determining the correct word order of translated words is a major challenge. The dependency parse tree of a source sentence can help to determine the correct word order of the translated words. In this paper, we present a novel reordering approach utilizing a neural network and dependency-based embeddings to predict whether the translations of two source words linked by a dependency relation should remain in the same order or should be swapped in the translated sentence. Experiments on Chinese-to-English translation show that our approach yields a statistically significant improvement of 0.57 BLEU point on benchmark NIST test sets, compared to our prior state-of-the-art statistical MT system that uses sparse dependency-based reordering features. |
Year | Venue | DocType |
---|---|---|
2017 | THIRTY-FIRST AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE | Conference |
Volume | ISSN | Citations |
abs/1702.04510 | Proceedings of AAAI-17 (2017) | 1 |
PageRank | References | Authors |
0.36 | 27 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Christian Hadiwinoto | 1 | 3 | 0.73 |
Hwee Tou Ng | 2 | 4092 | 300.40 |