NMTPY: A Flexible Toolkit for Advanced Neural Machine Translation Systems
2017-06-01Code Available0· sign in to hype
Ozan Caglayan, Mercedes García-Martínez, Adrien Bardet, Walid Aransa, Fethi Bougares, Loïc Barrault
Code Available — Be the first to reproduce this paper.
ReproduceCode
- github.com/lium-lst/nmtpyOfficialIn papernone★ 0
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.