arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1802.07170cs.CL
收藏

CytonMT:一个高效的神经机器翻译开源工具包的C++实现

CytonMT: an Efficient Neural Machine Translation Open-source Toolkit Implemented in C++

Advanced Translation Research and Development Promotion Center(高级翻译研发促进中心);National Institute of Information and Communications Technology, Japan(日本国立信息与通信技术研究所)

Xiaolin Wang, Masao Utiyama, Eiichiro Sumita

摘要:

本文介绍了一个名为CytonMT(https://github.com/arthurxlw/cytonMt)的开源神经机器翻译工具包。该工具包仅使用C++和NVIDIA的GPU加速库从头开始构建。该工具包具有培训效率,代码简单和翻译质量。基准测试表明,CytonMT在各种规模的神经网络上将训练速度加快了64.5%至110.8%,并达到了具有竞争力的翻译质量。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑