Abstract | ||
---|---|---|
We present Marian, an efficient and self-contained Neural Machine Translation framework with an integrated automatic differentiation engine based on dynamic computation graphs. Marian is written entirely in C++. We describe the design of the encoder-decoder framework and demonstrate that a research-friendly toolkit can achieve high training and translation speed. |
Year | DOI | Venue |
---|---|---|
2018 | 10.18653/v1/p18-4020 | ACL |
DocType | Volume | Citations |
Conference | abs/1804.00344 | 9 |
PageRank | References | Authors |
0.50 | 5 | 12 |
Name | Order | Citations | PageRank |
---|---|---|---|
Marcin Junczys-Dowmunt | 1 | 312 | 24.24 |
Roman Grundkiewicz | 2 | 9 | 1.17 |
Tomasz Dwojak | 3 | 9 | 1.17 |
Hieu Hoang | 4 | 1518 | 68.35 |
Kenneth Heafield | 5 | 579 | 39.46 |
Tom Neckermann | 6 | 9 | 0.50 |
frank seide | 7 | 1489 | 101.15 |
Ulrich Germann | 8 | 267 | 43.37 |
Alham Fikri Aji | 9 | 9 | 1.17 |
Nikolay Bogoychev | 10 | 9 | 1.17 |
André F. T. Martins | 11 | 801 | 52.10 |
Alexandra Birch | 12 | 2608 | 127.07 |