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

Marcin Junczys-Dowmunt, Kenneth Heafield, Hieu Hoang, Roman Grundkiewicz, Anthony Aue


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.
Anthology ID:
W18-2716
Volume:
Proceedings of the 2nd Workshop on Neural Machine Translation and Generation
Month:
July
Year:
2018
Address:
Melbourne, Australia
Venue:
NGT
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
129–135
Language:
URL:
https://aclanthology.org/W18-2716
DOI:
10.18653/v1/W18-2716
Bibkey:
Cite (ACL):
Marcin Junczys-Dowmunt, Kenneth Heafield, Hieu Hoang, Roman Grundkiewicz, and Anthony Aue. 2018. Marian: Cost-effective High-Quality Neural Machine Translation in C++. In Proceedings of the 2nd Workshop on Neural Machine Translation and Generation, pages 129–135, Melbourne, Australia. Association for Computational Linguistics.
Cite (Informal):
Marian: Cost-effective High-Quality Neural Machine Translation in C++ (Junczys-Dowmunt et al., NGT 2018)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingestion-script-update/W18-2716.pdf