OpenNMT: Open-Source Toolkit for Neural Machine Translation

Guillaume Klein, Yoon Kim, Yuntian Deng, Jean Senellart, Alexander M. Rush
1/10/2017
cs.CLcs.AIcs.NE

Official code: OpenNMT/OpenNMT (2,386 stars, MIT, last commit 2020-02-19).

Abstract

We describe an open-source toolkit for neural machine translation (NMT). The toolkit prioritizes efficiency, modularity, and extensibility with the goal of supporting NMT research into model architectures, feature representations, and source modalities, while maintaining competitive performance and reasonable training requirements. The toolkit consists of modeling and translation support, as well as detailed pedagogical documentation about the underlying techniques.

View on arXivView PDF

Code Implementations(1)

OpenNMT/OpenNMTOfficial100%
MIT

Open Source Neural Machine Translation in Torch (deprecated)

2,386454Lua, PerlOct 24, 20166 years agoMIT
deep-learningluamachine-translationneural-machine-translationopennmt+1 more

Similar Papers

OpenNMT: Neural Machine Translation Toolkit

97% match1 repo8052018

Joey NMT: A Minimalist NMT Toolkit for Novices

88% match1 repo7122019

Tensor2Tensor for Neural Machine Translation

88% match1 repo17.5k2018

The Microsoft Toolkit of Multi-Task Deep Neural Networks for Natural Language Understanding

85% match1 repo2.3k2020

Preparing an Endangered Language for the Digital Age: The Case of Judeo-Spanish

85% match1 repo22022

The eBible Corpus: Data and Model Benchmarks for Bible Translation for Low-Resource Languages

85% match1 repo62023

Cite this paper

@article{klein2017opennmt,
  title  = {OpenNMT: Open-Source Toolkit for Neural Machine Translation},
  author = {Guillaume Klein and Yoon Kim and Yuntian Deng and Jean Senellart and Alexander M. Rush},
  year   = {2017},
  eprint = {1701.02810},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/1701.02810}
}

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/1701.02810.svg)](https://codeofpaper.com/paper/1701.02810)

Discussion