NMTPY: A Flexible Toolkit for Advanced Neural Machine Translation Systems

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 architect...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2017-06
Main Authors: Caglayan, Ozan, García-Martínez, Mercedes, Bardet, Adrien, Aransa, Walid, Bougares, Fethi, Barrault, Loïc
Format: Article
Language:English
Subjects:
Boilers
Machine translation
Training
Utilities
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:2331-8422
DOI:10.48550/arxiv.1706.00457