NRC-CNRC machine translation systems for the 2021 AmericasNLP shared task

From National Research Council Canada

Download	View final version: NRC-CNRC machine translation systems for the 2021 AmericasNLP shared task (PDF, 289 KiB)
DOI	Resolve DOI: https://doi.org/10.18653/v1/2021.americasnlp-1.25
Author	Search for: Knowles, Rebecca¹; Search for: Stewart, Darlene¹; Search for: Larkin, Samuel¹; Search for: Littell, Patrick¹
Affiliation	National Research Council of Canada. Digital Technologies
Format	Text, Article
Conference	Proceedings of the First Workshop on Natural Language Processing for Indigenous Languages of the Americas (NAACL-HLT 2021), June 11th, 2021, Held Online
Abstract	We describe the NRC-CNRC systems submitted to the AmericasNLP shared task on machine translation. We submitted systems translating from Spanish into Wixárika, Nahuatl, Rarámuri, and Guaraní. Our best neural machine translation systems used multilingual pretraining, ensembling, finetuning, training on parts of the development data, and subword regularization. We also submitted translation memory systems as a strong baseline.
Publication date	2021-06-11
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 First Workshop on Natural Language Processing for Indigenous Languages of the Americas (11 June 2021): 224–233. https://doi.org/10.18653/v1/2021.americasnlp-1.
Language	English
Peer reviewed	Yes
Export citation	Export as RIS
Report a correction	Report a correction (opens in a new tab)
Record identifier	0b5c9ad3-d740-4e0f-aa8e-e887f7a65392
Record created	2022-02-14
Record modified	2022-02-15

Date modified:: 2024-07-19