AfriNLLB
A derivative multilingual translation model based on Meta's NLLB-200, further pre-trained and optimized for African languages. It achieves higher translation performance on African language translation tasks compared to general-purpose multilingual models.
Timeline (last 90 days)
The research team benchmarked four machine translation systems across three architectural families: NLLB-200 (600M parameters), mT5-base, and two AfriNLLB variants.
Fine-tuning on MudawanSn yields significant improvements in both translation directions, with the AfriNLLB variants optimized for African languages outperforming the general-purpose NLLB-200 and mT5.
All Facts (2)
The research team benchmarked four machine translation systems across three architectural families: NLLB-200 (600M parameters), mT5-base, and two AfriNLLB variants.
50%UnverifiedFine-tuning on MudawanSn yields significant improvements in both translation directions, with the AfriNLLB variants optimized for African languages outperforming the general-purpose NLLB-200 and mT5.
50%