Dear Spiral user, We’re pleased to introduce Helix, https://helix.imperial.ac.uk/ Imperial’s new repository for research datasets. Please use Helix for all future dataset deposits. There is no change to Spiral - continue depositing as usual. For queries, contact the Research Data Management team at rdm-enquiries@imperial.ac.uk. Kind regards, the Spiral Team. The Spiral team
NMTPY: A flexible toolkit for advanced neural machine translation systems
File(s)
OA Location
Author(s)
Caglayan, Ozan
García-Martínez, Mercedes
Bardet, Adrien
Aransa, Walid
Bougares, Fethi
Type
Journal Article
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.
Date Issued
2017-10-01
Date Acceptance
2017-09-01
Citation
Prague Bulletin of Mathematical Linguistics, 2017, 109 (1), pp.15-28
URI
DOI
ISSN
0032-6585
Publisher
Versita
Start Page
15
End Page
28
Journal / Book Title
Prague Bulletin of Mathematical Linguistics
Volume
109
Issue
1
Copyright Statement
© 2017 PBML. Distributed under CC BY-NC-ND. Corresponding author: ozancag@gmail.com
Cite as: Ozan Caglayan, Mercedes García-Martínez, Adrien Bardet, Walid Aransa, Fethi Bougares, Loïc Barrault.
NMTPY: A Flexible Toolkit for Advanced Neural Machine Translation Systems. The Prague Bulletin of Mathematical
Linguistics No. 109, 2017, pp. 15–28. doi: 10.1515/pralin-2017-0035.
Subjects
cs.CL
cs.CL
Publication Status
Published
Date Publish Online
2017-09-16