Adapting NMT to caption translation inWikimedia Commons for low-resource languages

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

Resumen


This paper presents a successful domain adaptation of a general neural machine translation (NMT) system using a bilingual corpus created with captions for images inWikimedia Commons for the Spanish-Basque and English-Irish pairs.

Texto completo:

PDF


Bookmark and Share