Skip to content
conftrace_
2020 EMNLP EMNLP 2020

CUNI Submission for the Inuktitut Language in WMT News 2020

Abstract

AbstractThis paper describes CUNI submission to the WMT 2020 News Translation Shared Task for the low-resource scenario Inuktitut–English in both translation directions. Our system combines transfer learning from a Czech–English high-resource language pair and backtranslation. We notice surprising behaviour when using synthetic data, which can be possibly attributed to a narrow domain of training and test data. We are using the Transformer model in a constrained submission.

🌉 Interdisciplinary Bridge - Artificial Intelligence and Natural Language Processing
🐣 Hot Topic Early Bird - low-resource language

Authors

Tom Kocmi

Topics

Machine Learning > Learning Types > Semi-Supervised Learning Deep Learning > Architectures > Transformers Natural Language Processing > Applications > Machine Translation Machine Learning > Learning Types > Transfer Learning Deep Learning > Learning Types > Transfer Learning

Keywords

transfer learning machine translation neural machine translation low-resource language transformer model
Download PDF

More from EMNLP 2020

All EMNLP 2020 papers →
An Iterative Knowledge Transfer NMT System for WMT20 News Translation Task
Tohoku-AIP-NTT at WMT 2020 News Translation Task
NRC Systems for the 2020 Inuktitut-English News Translation Task
Tilde at WMT 2020: News Task Systems
Samsung R&D Institute Poland submission to WMT20 News Translation Task
Speed-optimized, Compact Student Models that Distill Knowledge from a Larger Teacher Model: the UEDIN-CUNI Submission to the WMT 2020 News Translation Task