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

Par Conseil national de recherches du Canada

Téléchargement	Voir la version finale : NRC-CNRC systems for Upper Sorbian-German and Lower Sorbian-German machine translation 2021 (PDF, 406 Kio)
Auteur	Rechercher : Knowles, Rebecca¹; Rechercher : Larkin, Samuel¹
Affiliation	Conseil national de recherches Canada. Technologies numériques
Format	Texte, Article
Conférence	Sixth Conference on Machine Translation (WMT 2021), November 10-11, 2021 [Held Online]
Résumé	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.
Date de publication	2021-11
Maison d’édition	Association for Computational Linguistics
Licence	Creative Commons Attribution 4.0 International (CC BY 4.0) https://creativecommons.org/licenses/by/4.0/deed.fr
Dans	Proceedings of the Sixth Conference on Machine Translation, 2021.wmt-1.107 (novembre 2021) : 999–1008.
Langue	anglais
Publications évaluées par des pairs	Oui
Exporter la notice	Exporter en format RIS
Signaler une correction	Signaler une correction (s'ouvre dans un nouvel onglet)
Identificateur de l’enregistrement	f14a145b-7bb9-4b03-8aed-600fc2e3b844
Enregistrement créé	2022-01-17
Enregistrement modifié	2024-06-06

Date de modification :: 2026-01-16