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

DORAS | DCU Research Repository

Explore open access research and scholarly works from DCU

Advanced Search

Neural pre-translation for hybrid machine translation

Du, Jinhua orcid logoORCID: 0000-0002-3267-4881 and Way, Andy orcid logoORCID: 0000-0001-5736-5930 (2017) Neural pre-translation for hybrid machine translation. In: MT Summit XVI - 16th Machine Translation Summit, 18-22 Sept 2017, Nagoya, Japan.

Abstract
Hybrid machine translation (HMT) takes advantage of different types of machine translation (MT) systems to improve translation performance. Neural machine translation (NMT) can produce more fluent translations while phrase-based statistical machine translation (PB-SMT) can produce adequate results primarily due to the contribution of the translation model. In this paper, we propose a cascaded hybrid framework to combine NMT and PB-SMT to improve translation quality. Specifically, we first use the trained NMT system to pre-translate the training data, and then employ the pre-translated training data to build an SMT system and tune parameters using the pre-translated development set. Finally, the SMT system is utilised as a post-processing step to re-decode the pre-translated test set and produce the final result. Experiments conducted on Japanese!English and Chinese!English show that the proposed cascaded hybrid framework can significantly improve performance by 2.38 BLEU points and 4.22 BLEU points, respectively, compared to the baseline NMT system.
Metadata
Item Type:Conference or Workshop Item (Paper)
Event Type:Conference
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
Published in: Kurohashi, Sadao and Fung, Pascale, (eds.) Proceedings of MT Summit XVI: Research Track. 1. Asia-Pacific Association for Machine Translation.
Publisher:Asia-Pacific Association for Machine Translation
Official URL:http://aamt.info/app-def/S-102/mtsummit/2017/wp-co...
Copyright Information:© 2017 The Authors CC-BY-ND.
Use License:This item is licensed under a Creative Commons Attribution-NonCommercial-Share Alike 3.0 License. View License
Funders:ADAPT Centre for Digital Content Technology, funded under the SFI Research Centres Programme (Grant 13/RC/2106), SFI Industry Fellowship Programme 2016 (Grant 16/IFB/4490)
ID Code:23357
Deposited On:24 May 2019 15:12 by Thomas Murtagh . Last Modified 24 May 2019 15:12
Documents

Full text available as:

[thumbnail of neuralpretranslation4HMT[1].pdf]
Preview
PDF - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
293kB
Downloads

Downloads

Downloads per month over past year

Archive Staff Only: edit this record