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

February 17, 2018 · Entered Twilight · 🏛 Conference on Empirical Methods in Natural Language Processing

"Last commit was 7.0 years ago (≥5 year threshold)"

Evidence collected by the PWNC Scanner

Repo contents: LICENSE, Makefile, NOTICE, README.md, data, doc, runMe.sh, src

Authors Xiaolin Wang, Masao Utiyama, Eiichiro Sumita arXiv ID 1802.07170 Category cs.CL: Computation & Language Citations 6 Venue Conference on Empirical Methods in Natural Language Processing Repository https://github.com/arthurxlw/cytonMt ⭐ 21 Last Checked 1 month ago

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.