Login (DCU Staff Only)
Login (DCU Staff Only)

DORAS | DCU Research Repository

Explore open access research and scholarly works from DCU

Advanced Search

Is neural machine translation the new state of the art?

Castilho, Sheila orcid logoORCID: 0000-0002-8416-6555, Moorkens, Joss orcid logoORCID: 0000-0003-0766-0071, Gaspari, Federico orcid logoORCID: 0000-0003-3808-8418, Calixto, Iacer, Tinsley, John and Way, Andy orcid logoORCID: 0000-0001-5736-5930 (2017) Is neural machine translation the new state of the art? The Prague Bulletin of Mathematical Linguistics (108). ISSN 0032-6585

Abstract
This paper discusses neural machine translation (NMT), a new paradigm in the MT field, comparing the quality of NMT systems with statistical MT by describing three studies using automatic and human evaluation methods. Automatic evaluation results presented for NMT are very promising, however human evaluations show mixed results. We report increases in fluency but inconsistent results for adequacy and post-editing effort. NMT undoubtedly represents a step forward for the MT field, but one that the community should be careful not to oversell.
Metadata
Item Type:Article (Published)
Refereed:Yes
Subjects:Computer Science > Machine translating
DCU Faculties and Centres:DCU Faculties and Schools > Faculty of Engineering and Computing > School of Computing
Research Initiatives and Centres > ADAPT
Publisher:PBML
Official URL:https://doi.org/10.1515/pralin-2017-0013
Copyright Information:© 2017 PBML. Distributed under CC BY-NC-ND.
Use License:This item is licensed under a Creative Commons Attribution-NonCommercial-Share Alike 3.0 License. View License
Funders:TraMOOC project has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement № 644333, e Science Foundation Ireland Research Centres Programme (Grant 13/RC/ 2106) and is co-funded under the European Regional Development Fund
ID Code:23072
Deposited On:11 Mar 2019 12:53 by Thomas Murtagh . Last Modified 20 Jan 2021 16:52
Documents

Full text available as:

[thumbnail of Is Neural Machine Translation the New State of the Art.pdf]
Preview
PDF - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
139kB
Downloads

Downloads

Downloads per month over past year

Archive Staff Only: edit this record