Efficient and High-Quality Neural Machine Translation with OpenNMT

Efficient and High-Quality Neural Machine Translation with OpenNMT Guillaume Klein author Dakun Zhang author Clément Chouteau author Josep Crego author Jean Senellart author 2020-jul text Proceedings of the Fourth Workshop on Neural Generation and Translation Association for Computational Linguistics Online conference publication 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. klein-etal-2020-efficient https://www.aclweb.org/anthology/2020.ngt-1.25 2020-jul 211 217