Skip to content
conftrace_
2021 EMNLP EMNLP 2021

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

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.

🌉 Interdisciplinary Bridge - Artificial Intelligence and Natural Language Processing

Authors

Pinzhen Chen, Jindřich Helcl, Ulrich Germann, Laurie Burchell, Nikolay Bogoychev, Antonio Valerio Miceli Barone, Jonas Waldendorf, Alexandra Birch, Kenneth Heafield

Topics

Natural Language Processing > Applications > Machine Translation Machine Learning > Learning Types > Transfer Learning Deep Learning > Learning Types > Self-Supervised Learning Deep Learning > Learning Types > Transfer Learning

Keywords

neural machine translation multilingual model corpus filtering vocabulary embedding mapping
Download PDF

More from EMNLP 2021

All EMNLP 2021 papers →
Findings of the 2021 Conference on Machine Translation (WMT21)
Findings of the WMT 2021 Shared Task on Large-Scale Multilingual Machine Translation
GTCOM Neural Machine Translation Systems for WMT21
Tune in: The AFRL WMT21 News-Translation Systems
The TALP-UPC Participation in WMT21 News Translation Task: an mBART-based NMT Approach
CUNI Systems in WMT21: Revisiting Backtranslation Techniques for English-Czech NMT