NMTPY: A Flexible Toolkit for Advanced Neural Machine Translation Systems
arXiv:1706.00457 · doi:10.1515/pralin-2017-0035
Abstract
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.
10 pages, 3 figures