Skip to content
conftrace_
2021 EMNLP EMNLP 2021

Tune in: The AFRL WMT21 News-Translation Systems

Abstract

AbstractThis paper describes the Air Force Research Laboratory (AFRL) machine translation sys- tems and the improvements that were developed during the WMT21 evaluation campaign. This year, we explore various methods of adapting our baseline models from WMT20 and again measure improvements in performance on the Russian–English language pair.

🌉 Interdisciplinary Bridge - Artificial Intelligence and Natural Language Processing
🐣 Hot Topic Early Bird - model adaptation

Authors

Grant Erdmann, Jeremy Gwinnup, Tim Anderson

Topics

Natural Language Processing > Applications > Machine Translation Machine Learning > Learning Types > Transfer Learning Deep Learning > Learning Types > Transfer Learning Machine Learning > Learning Types > Machine Translation

Keywords

neural machine translation model adaptation multilingual model news translation transformer model baseline model
Download PDF

More from EMNLP 2021

All EMNLP 2021 papers →
Findings of the WMT 2021 Shared Task on Large-Scale Multilingual Machine Translation
GTCOM Neural Machine Translation Systems for WMT21
The University of Edinburgh’s English-German and English-Hausa Submissions to the WMT21 News Translation Task
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
Ensembling of Distilled Models from Multi-task Teachers for Constrained Resource Language Pairs