CytonMT: an Efficient Neural Machine Translation Open-source Toolkit Implemented in C++
Xiaolin Wang, Masao Utiyama, Eiichiro Sumita · 2018
This paper presents an open-source neural machine translation toolkit named CytonMT 1 .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.