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

DORAS | DCU Research Repository

Explore open access research and scholarly works from DCU

Advanced Search

Adapting NMT to caption translation in Wikimedia Commons for low-resource languages

Poncelas, Alberto orcid logoORCID: 0000-0002-5089-1687, Sarasola, Kepa orcid logoORCID: 0000-0003-4349-6088, Dowling, Meghan orcid logoORCID: 0000-0003-1637-4923, Way, Andy orcid logoORCID: 0000-0001-5736-5930, Labaka, Gorka orcid logoORCID: 0000-0003-4611-2502 and Alegria, Iñaki orcid logoORCID: 0000-0002-0272-1472 (2019) Adapting NMT to caption translation in Wikimedia Commons for low-resource languages. Procesamiento del Lenguaje Natural, 63 . pp. 33-40. ISSN 1135-5948

Abstract
This paper presents a successful domain adaptation of a general neural machine translation (NMT) system using a bilingual corpus created with captions for images in Wiki-media Commons for the Spanish-Basque and English-Irish pairs.
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 Institutes and Centres > ADAPT
Publisher:Sociedad Espanola para el Procesamiento del Lenguaje Natural
Copyright Information:© Sociedad Española para el Procesamiento del Lenguaje Natural
Use License:This item is licensed under a Creative Commons Attribution-NonCommercial-Share Alike 3.0 License. View License
Funders:TADEEP project (Spanish Ministry of Economy and Competitiveness TIN2015- 70214-P, with FEDER funding), Science Foundation Ireland (SFI) Research Centres Programme (Grant 13/RC/2106), European Regional Development Fund
ID Code:24442
Deposited On:11 May 2020 15:49 by Alberto Poncelas . Last Modified 22 Jan 2021 14:24
Documents

Full text available as:

[thumbnail of PLN_63_03.pdf]
Preview
PDF - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
1MB
Downloads

Downloads

Downloads per month over past year

Archive Staff Only: edit this record