Neural machine Translation with OpenNMT
This paper describes the OpenNMT submissions to the WNGT 2020 efficiency shared task. We explore training and acceleration of Transformer models with various sizes that are trained in a teacher-student setup. We also present a custom and optimized C++ inference engine that enables fast CPU and GPU decoding with few dependencies. By combining additional optimizations and parallelization techniques, we create small, efficient, and high-quality neural machine translation models.
Ouvrage : « Proceedings of the Fourth Workshop on Neural Generation and Translation », pages 211-217, Association for Computational Linguistics, juillet 2020