Joey NMT: A Minimalist NMT Toolkit for Novices
Joey NMT: A Minimalist NMT Toolkit for Novices
复制标题
DOI：
10.18653/v1/d19-3019
复制
发表时间：
2019-07
期刊：
影响因子：
--
通讯作者：
Julia Kreutzer;Jasmijn Bastings;S. Riezler
中科院分区：
文献类型：
--
作者：
Julia Kreutzer;Jasmijn Bastings;S. Riezler
我们介绍了Joey NMT，一个基于PyTorch的极简神经机器翻译工具包，专门为新手设计。Joey NMT在一个小而简单的代码库中提供了许多流行的NMT功能，因此新手可以轻松快速地学习使用它并根据他们的需求进行调整。尽管专注于简单性，Joey NMT支持经典架构（rnn、变压器）、快速波束搜索、权重绑定等，并且在标准基准测试中实现了与更复杂的工具包相当的性能。我们在用户研究中评估了我们的工具包的可访问性，其中具有Pytorch和NMT一般知识的新手和专家通过独立的Joey NMT教程进行工作，显示新手在随后的代码测试中的表现几乎与专家一样好。Joey NMT的网址是https://github.com/joeynmt/joeynmt。
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.