Papers by Nazarii Tupitsa
Low-Resource Machine Translation through the Lens of Personalized Federated Learning (2024.findings-emnlp)
Copied to clipboard
Viktor Moskvoretskii, Nazarii Tupitsa, Chris Biemann, Samuel Horváth, Eduard Gorbunov, Irina Nikishina
| Challenge: | Existing approaches to low-resource languages are limited to 500 languages . a lot of tasks for low-rsource languages remain unsolved . |
| Approach: | They propose a new approach called MeritOpt that can be applied to Natural Language Tasks with heterogeneous data. |
| Outcome: | The proposed approach can be applied to a low-resource machine translation task using the datasets of South East Asian and Finno-Ugric languages. |