Adapting NMT to caption translation in Wikimedia Commons for low-resource languages
Alberto Poncelas, Kepa Sarasola, Meghan Dowling, Andy Way, Gorka Labaka, Iñaki Alegria · Arrow@dit (Dublin Institute of Technology) · 2019
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.