We introduce an open-source toolkit for neural machine translation (NMT) to support research into model architectures, feature representations, and source modalities, while maintaining competitive performance, modularity and reasonable training requirements.
@article{arxiv.1709.03815,
title = {OpenNMT: Open-source Toolkit for Neural Machine Translation},
author = {Guillaume Klein and Yoon Kim and Yuntian Deng and Josep Crego and Jean Senellart and Alexander M. Rush},
journal= {arXiv preprint arXiv:1709.03815},
year = {2017}
}
Comments
Published in EAMT 2017 User Studies and Project/Product Descriptions