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

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

Research output: Chapter in Book/Report/Conference proceedingConference contribution

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.
Original languageEnglish
Title of host publicationProceedings of the 2nd Workshop on Neural Machine Translation and Generation
PublisherAssociation for Computational Linguistics (ACL)
Pages129-135
Number of pages7
Publication statusPublished - 2018
Event2nd Workshop on Neural Machine Translation and Generation - Melbourne, Australia
Duration: 15 Jul 201820 Jul 2018
https://sites.google.com/site/wnmt18/home
https://sites.google.com/site/wnmt18/

Conference

Conference2nd Workshop on Neural Machine Translation and Generation
Abbreviated titleWNMT 2018
Country/TerritoryAustralia
CityMelbourne
Period15/07/1820/07/18
Internet address

Fingerprint

Dive into the research topics of 'Marian: Cost-effective High-Quality Neural Machine Translation in C++'. Together they form a unique fingerprint.

Cite this