Tell your friends about this item:
Joint Training for Neural Machine Translation - Springer Theses Yong Cheng 2019 edition
Joint Training for Neural Machine Translation - Springer Theses
Yong Cheng
This book presents four approaches to jointly training bidirectional neural machine translation (NMT) models. First, in order to improve the accuracy of the attention mechanism, it proposes an agreement-based joint training approach to help the two complementary models agree on word alignment matrices for the same training data.
78 pages, 10 Tables, color; 9 Illustrations, color; 14 Illustrations, black and white; XIII, 78 p. 2
| Media | Books Hardcover Book (Book with hard spine and cover) |
| Released | September 6, 2019 |
| ISBN13 | 9789813297470 |
| Publishers | Springer Verlag, Singapore |
| Pages | 78 |
| Dimensions | 150 × 220 × 20 mm · 454 g |