Marian: Cost-effective High-Quality Neural Machine Translation in C++

Abstract

This paper describes the submissions of the "Marian" team to the WNMT 2018 shared task. We investigate combinations of teacher-student training, low-precision matrix products, auto-tuning and other methods to optimize the Transformer model on GPU and CPU. By further integrating these methods with the new averaging attention networks, a recently introduced faster Transformer variant, we create a number of high-quality, high-performance models on the GPU and CPU, dominating the Pareto frontier for this shared task.

arXiv commentSystem submission to the Workshop for Neural Machine Translation 2018, efficiency task

References in corpus (2)

• Is Neural Machine Translation Ready for Deployment? A Case Study on 30 Translation Directions
• Accelerating Neural Transformer via an Average Attention Network

Cited by in corpus (1)

• Findings of the Second Workshop on Neural Machine Translation and Generation