This paper describes XNMT, the eXtensible Neural Machine Translation toolkit. XNMT distin- guishes itself from other open-source NMT toolkits by its focus on modular code design, with the purpose of enabling fast iteration in research and replicable, reliable results. In this paper we describe the design of XNMT and its experiment configuration system, and demonstrate its utility on the tasks of machine translation, speech recognition, and multi-tasked machine translation/parsing. XNMT is available open-source at https://github.com/neulab/xnmt
@article{arxiv.1803.00188,
title = {XNMT: The eXtensible Neural Machine Translation Toolkit},
author = {Graham Neubig and Matthias Sperber and Xinyi Wang and Matthieu Felix and Austin Matthews and Sarguna Padmanabhan and Ye Qi and Devendra Singh Sachan and Philip Arthur and Pierre Godard and John Hewitt and Rachid Riad and Liming Wang},
journal= {arXiv preprint arXiv:1803.00188},
year = {2018}
}
Comments
To be presented at AMTA 2018 Open Source Software Showcase