Marian: Fast Neural Machine Translation in C++

Marcin Junczys-Dowmunt, Roman Grundkiewicz, Tomasz Dwojak, Hieu Hoang, Kenneth Heafield, Tom Neckermann, Frank Seide, Ulrich Germann, Alham Fikri Aji, Nikolay Bogoychev, André F.T. Martins, Alexandra Birch

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


We present Marian, an efficient and self-contained Neural Machine Translation framework with an integrated automatic differentiation engine based on dynamic computation graphs. Marian is written entirely in C++. We describe the design of the encoder-decoder framework and demonstrate that a research-friendly toolkit can achieve high training and translation speed.
Original languageEnglish
Title of host publicationProceedings of ACL 2018, System Demonstrations
PublisherAssociation for Computational Linguistics
Number of pages6
ISBN (Print)978-1-948087-65-0
Publication statusPublished - 20 Jul 2018
Event56th Annual Meeting of the Association for Computational Linguistics - Melbourne Convention and Exhibition Centre, Melbourne, Australia
Duration: 15 Jul 201820 Jul 2018


Conference56th Annual Meeting of the Association for Computational Linguistics
Abbreviated titleACL 2018
Internet address


Dive into the research topics of 'Marian: Fast Neural Machine Translation in C++'. Together they form a unique fingerprint.

Cite this