The University of Edinburgh's English-German and English-Hausa Submissions to the WMT21 News Translation Task

Abstract

This paper presents the University of Edinburgh's constrained submissions of English-German and English-Hausa systems to the WMT 2021 shared task on news translation. We build En-De systems in three stages: corpus filtering, back-translation, and fine-tuning.

For En-Ha we use an iterative back-translation approach on top of pre-trained En-De models and investigate vocabulary embedding mapping.

Keywords

• university
• edinburgh
• english
• german
• english
• hausa
• submissions
• wmt21
• news
• translation
• task