NMT-Keras: a Very Flexible Toolkit with a Focus on Interactive NMT and Online Learning
This toolkit provides a modular framework for researchers and practitioners in machine translation and related fields, but it is incremental as it builds on existing libraries and models.
The authors introduced NMT-Keras, a flexible toolkit for training deep learning models with a focus on neural machine translation applications like interactive protocols and continuous learning, built on an extended Keras library and supporting Theano and TensorFlow.
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.