Marian: Fast Neural Machine Translation in C++

@article{JunczysDowmunt2018MarianFN,
  title={Marian: Fast Neural Machine Translation in C++},
  author={Marcin Junczys-Dowmunt and Roman Grundkiewicz and Tomasz Dwojak and Hieu T. Hoang and Kenneth Heafield and Tom Neckermann and F. Seide and Ulrich Germann and A. F. Aji and Nikolay Bogoychev and Andr{\'e} F. T. Martins and Alexandra Birch},
  journal={ArXiv},
  year={2018},
  volume={abs/1804.00344}
}
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. 
Fast Neural Machine Translation Implementation
The OpenNMT Neural Machine Translation Toolkit: 2020 Edition
Neural Machine Translation: A Review of Methods, Resources, and Tools
Off-the-Shelf Unsupervised NMT
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 18 REFERENCES
Multi-Source Neural Translation
OpenNMT: Open-Source Toolkit for Neural Machine Translation
Nematus: a Toolkit for Neural Machine Translation
Neural Machine Translation of Rare Words with Subword Units
Sequence to Sequence Transduction with Hard Monotonic Attention
...
1
2
...