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

NMT@ACL, 2018.

Cited by: 0|Views83
EI

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 rece...More

Code:

Data:

Your rating :
0

 

Tags
Comments