Joey NMT: A Minimalist NMT Toolkit for Novices
This toolkit addresses the accessibility problem for novices in machine learning by providing a simple yet effective NMT solution, though it is incremental as it builds on existing methods.
The authors tackled the problem of making neural machine translation (NMT) toolkits accessible to novices by developing Joey NMT, a minimalist toolkit based on PyTorch, which achieved performance comparable to more complex toolkits on standard benchmarks and showed in a user study that novices performed almost as well as experts in a code quiz.
We present Joey NMT, a minimalist neural machine translation toolkit based on PyTorch that is specifically designed for novices. Joey NMT provides many popular NMT features in a small and simple code base, so that novices can easily and quickly learn to use it and adapt it to their needs. Despite its focus on simplicity, Joey NMT supports classic architectures (RNNs, transformers), fast beam search, weight tying, and more, and achieves performance comparable to more complex toolkits on standard benchmarks. We evaluate the accessibility of our toolkit in a user study where novices with general knowledge about Pytorch and NMT and experts work through a self-contained Joey NMT tutorial, showing that novices perform almost as well as experts in a subsequent code quiz. Joey NMT is available at https://github.com/joeynmt/joeynmt .