NMT-Keras: a Very Flexible Toolkit with a Focus on Interactive NMT and Online Learning

TL;DR

NMT-Keras is a flexible, modular toolkit built on Keras that facilitates advanced neural machine translation applications, including interactive translation and continuous learning, with extensions to other AI tasks.

Contribution

It introduces a highly flexible toolkit based on Keras for developing interactive NMT systems and online learning, supporting diverse deep learning applications.

Findings

Supports interactive-predictive translation protocols

Enables long-term adaptation via continuous learning

Extensible to image captioning and visual question answering

Abstract

We present NMT-Keras, a flexible toolkit for training deep learning models, which puts a particular emphasis on the development of advanced applications of neural machine translation systems, such as interactive-predictive translation protocols and long-term adaptation of the translation system via continuous learning. NMT-Keras is based on an extended version of the popular Keras library, and it runs on Theano and Tensorflow. State-of-the-art neural machine translation models are deployed and used following the high-level framework provided by Keras. Given its high modularity and flexibility, it also has been extended to tackle different problems, such as image and video captioning, sentence classification and visual question answering.