CytonMT: an Efficient Neural Machine Translation Open-source Toolkit Implemented in C++
Abstract
This paper presents an open-source neural machine translation toolkit named CytonMT (https://github.com/arthurxlw/cytonMt). The toolkit is built from scratch only using C++ and NVIDIA's GPU-accelerated libraries. The toolkit features training efficiency, code simplicity and translation quality. Benchmarks show that CytonMT accelerates the training speed by 64.5% to 110.8% on neural networks of various sizes, and achieves competitive translation quality.
- Publication:
-
arXiv e-prints
- Pub Date:
- February 2018
- DOI:
- 10.48550/arXiv.1802.07170
- arXiv:
- arXiv:1802.07170
- Bibcode:
- 2018arXiv180207170W
- Keywords:
-
- Computer Science - Computation and Language