Search papers, labs, and topics across Lattice.
MilaAccess 2 PerspectivesCIFARImperialIndependent ConsultantIndependent ResearcherMasakhane Research FoundationUniversity of Cape TownUniversity of PretoriaUniversity of South AfricaUW-MadisonMay 28, 2026arXiv:2605.29741AfriScience-MT, a new parallel corpus of scientific text translated into six African languages (Amharic, Hausa, Luganda, Northern Sotho, Yoruba, and isiZulu) across 11 domains, was created to address the lack of scientific terminology and resources in these languages. Professional translators and science communicators translated plain-language summaries of scientific papers, generating new terms as needed. Benchmarking experiments reveal that closed-source models like GPT-5.4 and Gemini-3.1-Flash-Lite currently outperform open-source models, although fine-tuned NLLB-1.3B and TranslateGemma-12B show promise.
Bridging the scientific knowledge gap for hundreds of millions, AfriScience-MT pioneers document-level scientific machine translation for six African languages.
The dominance of colonial languages in African education and scientific communication limits how hundreds of millions of speakers of African languages access and produce scientific knowledge. A core obstacle is the lack of established scientific terminology in these languages. We introduce AfriScience-MT, a parallel corpus covering six African languages (Amharic, Hausa, Luganda, Northern Sotho, Yor\`ub\'a, and isiZulu) across 11 scientific domains. Professional translators, working with expert science communicators, translated plain-language summaries of scientific papers into each target language and created new terms where none existed. We benchmark machine translation systems and large language models in zero-shot, few-shot, and fine-tuned settings. Our results show that closed-source models outperform all open-source models at both the sentence and document levels: GPT-5.4 and Gemini-3.1-Flash-Lite lead with average sentence-level COMET scores of 68.3 and 68.0, respectively, and tie at an average document-level COMET of 48.3. Among open systems, fine-tuned NLLB-1.3B reaches 67.3 at the sentence level, and TranslateGemma-12B reaches 44.0 at the document level with 1-shot in-context learning. We release AfriScience-MT to support benchmarking and document-level scientific MT for African languages.
