Abstract
This paper presents an open-source neural machine translation toolkit named 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.- Anthology ID:
- D18-2023
- Volume:
- Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing: System Demonstrations
- Month:
- November
- Year:
- 2018
- Address:
- Brussels, Belgium
- Venue:
- EMNLP
- SIG:
- SIGDAT
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 133–138
- Language:
- URL:
- https://aclanthology.org/D18-2023
- DOI:
- 10.18653/v1/D18-2023
- Cite (ACL):
- Xiaolin Wang, Masao Utiyama, and Eiichiro Sumita. 2018. CytonMT: an Efficient Neural Machine Translation Open-source Toolkit Implemented in C++. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pages 133–138, Brussels, Belgium. Association for Computational Linguistics.
- Cite (Informal):
- CytonMT: an Efficient Neural Machine Translation Open-source Toolkit Implemented in C++ (Wang et al., EMNLP 2018)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/D18-2023.pdf
- Code
- arthurxlw/cytonMt