Marian: Fast Neural Machine Translation in C++

Marcin Junczys-Dowmunt, Roman Grundkiewicz, Tomasz Dwojak, Hieu Hoang, Kenneth Heafield +7 more
4/1/2018
cs.CL

Official code: marian-nmt/marian (1,474 stars, last commit 2023-08-25).

Abstract

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.

View on arXivView PDF

Code Implementations(1)

marian-nmt/marianOfficial100%

Fast Neural Machine Translation in C++

1,474250C, C++Apr 14, 20163 years agoNOASSERTION
cudafastgpuneural-machine-translation

Similar Papers

A Step-by-step Introduction to the Implementation of Automatic Differentiation

77% match2024

Forward-Mode Automatic Differentiation in Julia

76% match1 repo1.0k2016

Fashionable Modelling with Flux

76% match1 repo4.8k2018

A Benchmark of Selected Algorithmic Differentiation Tools on Some Problems in Computer Vision and Machine Learning

75% match1 repo32018

TransformCode: A Contrastive Learning Framework for Code Embedding via Subtree Transformation

75% match1 repo92023

DaCe AD: Unifying High-Performance Automatic Differentiation for Machine Learning and Scientific Computing

75% match2025

Cite this paper

@article{junczysdowmunt2018marian,
  title  = {Marian: Fast Neural Machine Translation in C++},
  author = {Marcin Junczys-Dowmunt and Roman Grundkiewicz and Tomasz Dwojak and Hieu Hoang and Kenneth Heafield and Tom Neckermann and Frank Seide and Ulrich Germann and Alham Fikri Aji and Nikolay Bogoychev and André F. T. Martins and Alexandra Birch},
  year   = {2018},
  eprint = {1804.00344},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/1804.00344}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/1804.00344.svg)](https://codeofpaper.com/paper/1804.00344)

Discussion