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
- Editors:
- Alexandra Birch, Andrew Finch, Thang Luong, Graham Neubig, Yusuke Oda
- 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
- 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)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-5/W18-2716.pdf