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

DORAS | DCU Research Repository

Explore open access research and scholarly works from DCU

Advanced Search

Selecting artificially-generated sentences for fine-tuning neural machine translation

Poncelas, Alberto orcid logoORCID: 0000-0002-5089-1687 and Way, Andy orcid logoORCID: 0000-0001-5736-5930 (2019) Selecting artificially-generated sentences for fine-tuning neural machine translation. In: 12th International Conference on Natural Language Generation, 29 Oct - 1 Nov 2019, Tokyo, Japan.

Abstract
Neural Machine Translation (NMT) models tend to achieve best performance when larger sets of parallel sentences are provided for trai- ning. For this reason, augmenting the training set with artificially-generated sentence pairs can boost performance. Nonetheless, the performance can also be im- proved with a small number of sentences if they are in the same domain as the test set. Accordingly, we want to explore the use of artificially-generated sentences along with data-selection algorithms to improve German- to-English NMT models trained solely with authentic data. In this work, we show how artificially- generated sentences can be more beneficial than authentic pairs, and demonstrate their ad- vantages when used in combination with data- selection algorithms.
Metadata
Item Type:Conference or Workshop Item (Paper)
Event Type:Conference
Refereed:Yes
Uncontrolled Keywords:Backtranslation
Subjects:Computer Science > Computational linguistics
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: Proceedings of 12th International Conference on Natural Language Generation. .
Official URL:https://www.inlg2019.com/assets/papers/197_Paper.p...
Copyright Information:© 2019 The authors
Use License:This item is licensed under a Creative Commons Attribution-NonCommercial-Share Alike 3.0 License. View License
Funders:SFI Research Centres Programme (Grant 13/RC/2106)
ID Code:23903
Deposited On:05 Nov 2019 09:47 by Andrew Way . Last Modified 22 Jan 2021 14:21
Documents

Full text available as:

[thumbnail of 197_Paper.pdf]
Preview
PDF - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
192kB
Downloads

Downloads

Downloads per month over past year

Archive Staff Only: edit this record