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

DORAS | DCU Research Repository

Explore open access research and scholarly works from DCU

Advanced Search

Investigating backtranslation for the improvement of English-Irish machine translation

Dowling, Meghan orcid logoORCID: 0000-0003-1637-4923, Lynn, Teresa and Way, Andy orcid logoORCID: 0000-0001-5736-5930 (2019) Investigating backtranslation for the improvement of English-Irish machine translation. Teanga, 26 . pp. 1-25. ISSN 0332-205X

Abstract
In this paper, we discuss the difficulties of building reliable machine translation systems for the English-Irish (EN-GA) language pair. In the context of limited datasets, we report on assessing the use of backtranslation as a method for creating artificial EN-GA data to increase training data for use state-of-the-art data-driven translation systems. We compare our results to earlier work on EN-GA machine translation by Dowling et al (2016, 2017, 2018) showing that while our own systems do not compare in quality with respect to traditionally reported BLEU metrics, we provide a linguistic analysis to suggest that future work with domain specific data may prove more successful.
Metadata
Item Type:Article (Published)
Refereed:Yes
Uncontrolled Keywords:Gaeilge; English; automatic evaluation metrics
Subjects:Computer Science > Computational linguistics
Computer Science > Machine translating
Humanities > Irish language
DCU Faculties and Centres:DCU Faculties and Schools > Faculty of Engineering and Computing > School of Computing
Research Initiatives and Centres > ADAPT
Publisher:Irish Association for Applied Linguistics
Official URL:https://doi.org/10.35903/teanga.v26i0.88
Copyright Information:© 2019 The Authors. CC-BY 4.0
Funders:Science Foundation Ireland through the SFI Research Centres Programme, European Regional Development Fund (ERDF) through Grant # 13/RC/2106, Department of Culture, Heritage and the Gaeltacht
ID Code:24030
Deposited On:17 Dec 2019 13:22 by Meghan Dowling . Last Modified 17 Dec 2019 13:22
Documents

Full text available as:

[thumbnail of 88-Article Text-700-1-10-20191128.pdf]
Preview
PDF - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
538kB
Downloads

Downloads

Downloads per month over past year

Archive Staff Only: edit this record