The University of Edinburgh’s English-German and English-Hausa Submissions to the WMT21 News Translation Task
27793Authors
nan
Abstract
AbstractThis 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
Full Content
nan
Labeled Text
AbstractThis 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.
Publication Details
- Paper ID:
- 27793
- Year:
- 2021
- Publication:
- TIPSTER
- Publication Type:
- conf
- DOI:
- nan