Augmenting Neural Machine Translation through Round-Trip Training Approach
The quality of Neural Machine Translation (NMT), as a data-driven approach, massively depends on quantity, quality and relevance of the training dataset. Such approaches have achieved promising results for bilingually high-resource scenarios but are inadequate for low-resource conditions. Generally,...
| Hlavní autoři: | , |
|---|---|
| Médium: | Článek |
| Jazyk: | English |
| Vydáno: |
De Gruyter
2019-10-01
|
| Edice: | Open Computer Science |
| Témata: | |
| On-line přístup: | http://www.degruyter.com/view/j/comp.2019.9.issue-1/comp-2019-0019/comp-2019-0019.xml?format=INT |