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

DORAS | DCU Research Repository

Explore open access research and scholarly works from DCU

Advanced Search

Improving English-to-Indian language neural machine translation systems

Kandimalla, Akshara, Lohar, Pintu orcid logoORCID: 0000-0002-5328-1585, Maji, Souvik Kumar and Way, Andy orcid logoORCID: 0000-0001-5736-5930 (2022) Improving English-to-Indian language neural machine translation systems. Information, 13 (5). ISSN 2078-2489

Most Indian languages lack sufficient parallel data for Machine Translation (MT) training. In this study, we build English-to-Indian language Neural Machine Translation (NMT) systems using the state-of-the-art transformer architecture. In addition, we investigate the utility of back-translation and its effect on system performance. Our experimental evaluation reveals that the back-translation method helps to improve the BLEU scores for both English-to-Hindi and English-to-Bengali NMT systems. We also observe that back-translation is more useful in improving the quality of weaker baseline MT systems. In addition, we perform a manual evaluation of the translation outputs and observe that the BLEU metric cannot always analyse the MT quality as well as humans. Our analysis shows that MT outputs for the English–Bengali pair are actually better than that evaluated by BLEU metric.
Item Type:Article (Published)
Uncontrolled Keywords:machine translation; back-translation; parallel data
Subjects:Computer Science > Machine translating
DCU Faculties and Centres:DCU Faculties and Schools > Faculty of Engineering and Computing > School of Computing
Research Institutes and Centres > ADAPT
Official URL:https://dx.doi.org/10.3390/info13050245
Copyright Information:© 2022 The Authors.
ID Code:27451
Deposited On:29 Jul 2022 09:22 by Thomas Murtagh . Last Modified 05 May 2023 16:40

Full text available as:

[thumbnail of information-13-00245.pdf]
PDF - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
Creative Commons: Attribution 4.0


Downloads per month over past year

Archive Staff Only: edit this record