Skip to content
conftrace_
2021 EMNLP EMNLP 2021

NRC-CNRC Systems for Upper Sorbian-German and Lower Sorbian-German Machine Translation 2021

Abstract

AbstractWe describe our neural machine translation systems for the 2021 shared task on Unsupervised and Very Low Resource Supervised MT, translating between Upper Sorbian and German (low-resource) and between Lower Sorbian and German (unsupervised). The systems incorporated data filtering, backtranslation, BPE-dropout, ensembling, and transfer learning from high(er)-resource languages. As measured by automatic metrics, our systems showed strong performance, consistently placing first or tied for first across most metrics and translation directions.

🌉 Interdisciplinary Bridge - Artificial Intelligence and Natural Language Processing

Authors

Rebecca Knowles, Samuel Larkin

Topics

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

Keywords

transfer learning ensemble learning neural machine translation model ensembling data filtering unsupervised machine translation
Download PDF

More from EMNLP 2021

All EMNLP 2021 papers →
Unsupervised Translation of German–Lower Sorbian: Exploring Training and Novel Transfer Methods on a Low-Resource Language
The LMU Munich Systems for the WMT21 Unsupervised and Very Low-Resource Translation Task
Language Model Pretraining and Transfer Learning for Very Low Resource Languages
NoahNMT at WMT 2021: Dual Transfer for Very Low Resource Supervised Machine Translation
cushLEPOR: customising hLEPOR metric using Optuna for higher agreement with human judgments or pre-trained language model LaBSE
MTEQA at WMT21 Metrics Shared Task