XNMT: The eXtensible Neural Machine Translation Toolkit

Abstract

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

To be presented at AMTA 2018 Open Source Software Showcase

References in corpus (4)

• Adam: A Method for Stochastic Optimization
• Sequence to Sequence Learning with Neural Networks
• Sequence Level Training with Recurrent Neural Networks
• DyNet: The Dynamic Neural Network Toolkit

Cited by in corpus (14)

• A Large-Scale Comparison of Historical Text Normalization Systems
• EVIL: Exploiting Software via Natural Language
• Texar: A Modularized, Versatile, and Extensible Toolkit for Text Generation
• When and Why are Pre-trained Word Embeddings Useful for Neural Machine Translation?
• Rapid Adaptation of Neural Machine Translation to New Languages
• On the Weaknesses of Reinforcement Learning for Neural Machine Translation
• Building the MSR Tool Kaiaulu: Design Principles and Experiences
• The ARIEL-CMU Systems for LoReHLT18
• LeafNATS: An Open-Source Toolkit and Live Demo System for Neural Abstractive Text Summarization
• Neural Machine Translation: A Review and Survey
• Autosegmental Neural Nets: Should Phones and Tones be Synchronous or Asynchronous?
• Learning Neural Models for Natural Language Processing in the Face of Distributional Shift
• Fluent Translations from Disfluent Speech in End-to-End Speech Translation
• Cross-lingual Word Embeddings beyond Zero-shot Machine Translation