NRC-CNRC systems for Upper Sorbian-German and Lower Sorbian-German machine translation 2021

Download	View final version: NRC-CNRC systems for Upper Sorbian-German and Lower Sorbian-German machine translation 2021 (PDF, 406 KiB)
Author	Search for: Knowles, Rebecca¹; Search for: Larkin, Samuel¹
Affiliation	National Research Council Canada. Digital Technologies
Format	Text, Article
Conference	Sixth Conference on Machine Translation (WMT 2021), November 10-11, 2021 [Held Online]
Abstract	We 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.
Publication date	2021-11
Publisher	Association for Computational Linguistics
Licence	Creative Commons Attribution 4.0 International (CC BY 4.0) https://creativecommons.org/licenses/by/4.0/
In	Proceedings of the Sixth Conference on Machine Translation, 2021.wmt-1.107 (November 2021): 999–1008.
Language	English
Peer reviewed	Yes
Export citation	Export as RIS
Report a correction	Report a correction (opens in a new tab)
Record identifier	f14a145b-7bb9-4b03-8aed-600fc2e3b844
Record created	2022-01-17
Record modified	2024-06-06