XNMT: The eXtensible Neural Machine Translation Toolkit
It provides a tool for researchers in machine translation and related fields to accelerate experimentation and ensure reliability, though it is incremental as it builds on existing NMT frameworks.
The paper introduces XNMT, an extensible toolkit for neural machine translation, designed with modular code to enable fast research iteration and replicable results, and demonstrates its utility on tasks including machine translation, speech recognition, and multi-tasked translation/parsing.
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