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

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.
Keywords: Machine Translation, Low-resource languages, Bilingual corpora, Language
resources from Wikipedia

Authors: 
Alberto Poncelas, Kepa Sarasola, Meghan Dowling, Andy Way, Gorka Labaka, Iñaki Alegria

Publication topic:

Year: 
2019
Evaluation: 

Procesamiento del Lenguaje Natural
ISSN 1989-7553

Publication place: 

SEPLN 2019

Publication type:

Publication clasification:

Bibliographic databases:

HiTZ: