CytonMT: an Efficient Neural Machine Translation Open-source Toolkit Implemented in C++
@article{Wang2018CytonMTAE, title={CytonMT: an Efficient Neural Machine Translation Open-source Toolkit Implemented in C++}, author={X. Wang and M. Utiyama and E. Sumita}, journal={ArXiv}, year={2018}, volume={abs/1802.07170} }
This paper presented an open-source neural machine translation toolkit named CytonMT\footnote{this https URL}. The toolkit was built from scratch using C++ and Nvidia's GPU-accelerated libraries. The toolkit featured training efficiency, code simplicity and translation quality. Benchmarks showed that cytonMT accelerated the training speed by 64.5\% to 110.8\% and achieved a high translation quality only lower than the Google's production engine among the NMT systems of attention-based RNN… Expand
Figures, Tables, and Topics from this paper
6 Citations
CytonRL: an Efficient Reinforcement Learning Open-source Toolkit Implemented in C++
- Computer Science, Mathematics
- ArXiv
- 2018
- PDF
Sifar: An Attempt to Develop Interactive Machine Translation System for English to Hindi
- Computer Science
- 2020
- 1
Handling Unknown Words in Neural Machine Translation System
- 2020 International Conference on Decision Aid Sciences and Application (DASA)
- 2020
The Roles of Language Models and Hierarchical Models in Neural Sequence-to-Sequence Prediction
- Computer Science
- EAMT
- 2020
- 3
- PDF
References
SHOWING 1-10 OF 27 REFERENCES
OpenNMT: Open-Source Toolkit for Neural Machine Translation
- Computer Science
- ACL
- 2017
- 1,124
- Highly Influential
- PDF
Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
- Computer Science
- ArXiv
- 2016
- 3,431
- PDF
Addressing the Rare Word Problem in Neural Machine Translation
- Computer Science
- ACL
- 2015
- 612
- Highly Influential
- PDF
Neural Machine Translation by Jointly Learning to Align and Translate
- Computer Science, Mathematics
- ICLR
- 2015
- 14,961
- PDF
Effective Approaches to Attention-based Neural Machine Translation
- Computer Science
- EMNLP
- 2015
- 4,651
- Highly Influential
- PDF