NMTPY: A Flexible Toolkit for Advanced Neural Machine Translation Systems
This toolkit simplifies development for researchers and practitioners in machine translation by reducing boilerplate code.
The paper introduces nmtpy, a flexible Python toolkit for training neural machine translation and sequence-to-sequence models, which was used to achieve top-ranked submissions in WMT tasks in 2016 and 2017.
In this paper, we present nmtpy, a flexible Python toolkit based on Theano for training Neural Machine Translation and other neural sequence-to-sequence architectures. nmtpy decouples the specification of a network from the training and inference utilities to simplify the addition of a new architecture and reduce the amount of boilerplate code to be written. nmtpy has been used for LIUM's top-ranked submissions to WMT Multimodal Machine Translation and News Translation tasks in 2016 and 2017.