Skip to content
conftrace_
2020 EMNLP EMNLP 2020

NRC Systems for Low Resource German-Upper Sorbian Machine Translation 2020: Transfer Learning with Lexical Modifications

Abstract

AbstractWe describe the National Research Council of Canada (NRC) neural machine translation systems for the German-Upper Sorbian supervised track of the 2020 shared task on Unsupervised MT and Very Low Resource Supervised MT. Our models are ensembles of Transformer models, built using combinations of BPE-dropout, lexical modifications, and backtranslation.

🌉 Interdisciplinary Bridge - Artificial Intelligence and Natural Language Processing

Authors

Rebecca Knowles, Samuel Larkin, Darlene Stewart, Patrick Littell

Topics

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

Keywords

transfer learning ensemble learning neural machine translation transformer model lexical modification
Download PDF

More from EMNLP 2020

All EMNLP 2020 papers →
UdS-DFKI@WMT20: Unsupervised MT and Very Low Resource Supervised MT for German-Upper Sorbian
Data Selection for Unsupervised Translation of German–Upper Sorbian
The LMU Munich System for the WMT20 Very Low Resource Supervised MT Task
CUNI Systems for the Unsupervised and Very Low Resource Translation Task in WMT20
The University of Helsinki and Aalto University submissions to the WMT 2020 news and low-resource translation tasks
The NITS-CNLP System for the Unsupervised MT Task at WMT 2020