AfriScience-MT: Towards Decolonizing Science in Africa through Text Translation

• URL: http://arxiv.org/abs/2605.29741v1
• Date: Thu, 28 May 2026 10:36:32 GMT
• Title: AfriScience-MT: Towards Decolonizing Science in Africa through Text Translation
• Abstract summary: AfriScience-MT is a parallel corpus covering six African languages (Amharic, Hausa, Luganda, Northern Sotho, Yorb, and isiZulu)<n>Professional translators translated plain-language summaries of scientific papers into each target language and created new terms where none existed.<n>We benchmark machine translation systems and large language models in zero-shot, few-shot, and fine-tuned settings.
• Score: 13.80926536385416
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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, Yorùbá, 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.

Related papers

• Bridging Scientific Heritage: An Arabic--Russian Parallel Corpus and LLM Benchmark for Sustainable Knowledge Transfer [0.0]
  We present a benchmark for Arabic--Russian scientific translation.<n>The benchmark includes a hybrid parallel corpus of about 27,000 sentence pairs.<n>It enables knowledge exchange between Arabic-speaking and Russian-speaking researchers.
  arXiv  Detail & Related papers  (2026-06-29T21:53:34Z)
• AFRILANGTUTOR: Advancing Language Tutoring and Culture Education in Low-Resource Languages with Large Language Models [12.74993793082974]
  We build a dataset of 78.9K multi-turn training examples for Supervised Fine-Tuning (SFT) and Direct Preference Optimization (DPO)<n>We train language tutoring models collectively referred to as AFRILangedu across 10 African languages.<n>Our results show that models trained on AFRILangedu consistently outperform their base counterparts.
  arXiv  Detail & Related papers  (2026-04-22T18:38:04Z)
• Towards High-Quality Machine Translation for Kokborok: A Low-Resource Tibeto-Burman Language of Northeast India [0.0]
  KokborokMT is a high-quality neural machine translation (NMT) system for Kokborok (ISO 639-3), a Tibeto-Burman language spoken primarily in Tripura, India.<n>We fine-tune the NLLB-200-distilled-600M model on a multi-source parallel corpus comprising 36,052 sentence pairs.<n>Our best system achieves BLEU scores of 17.30 and 38.56 on held-out test sets, representing substantial improvements over prior published results.
  arXiv  Detail & Related papers  (2026-03-28T18:20:13Z)
• ASCAT: An Arabic Scientific Corpus and Benchmark for Advanced Translation Evaluation [1.730057408524355]
  ASCAT targets full scientific abstracts averaging 141.7 words (English) and 111.78 words (Arabic)<n>Each abstract was translated using three complementary generative AI (Gemini), transformer-based models (Hugging Face texttquickmt-en-ar), and commercial MT APIs (Google Translate, DeepL)<n>The resulting corpus contains 67,293 English tokens and 60,026 Arabic tokens, with an Arabic vocabulary of 17,604 unique words reflecting the morphological richness of the language.
  arXiv  Detail & Related papers  (2026-03-10T18:41:52Z)
• The African Languages Lab: A Collaborative Approach to Advancing Low-Resource African NLP [4.188487384419692]
  Despite representing nearly one-third of the world's languages, African languages remain critically underserved by modern NLP technologies.<n>We present the African Languages Lab, a comprehensive research initiative that addresses this technological gap through systematic data collection, model development, and capacity building.
  arXiv  Detail & Related papers  (2025-10-07T07:42:52Z)
• A MISMATCHED Benchmark for Scientific Natural Language Inference [53.17435107472026]
  We introduce a novel evaluation benchmark for scientific NLI, called MISMATCHED.<n>The new benchmark covers three non-CS domains-PSYCHOLOGY, ENGINEERING, and PUBLIC HEALTH, and contains 2,700 human annotated sentence pairs.<n>In addition to introducing the MISMATCHED benchmark, we show that incorporating sentence pairs having an implicit scientific NLI relation between them in model training improves their performance on scientific NLI.
  arXiv  Detail & Related papers  (2025-06-05T03:40:57Z)
• Bridging the Gap: Enhancing LLM Performance for Low-Resource African Languages with New Benchmarks, Fine-Tuning, and Cultural Adjustments [0.9214083577876088]
  This paper creates approximately 1 million human-translated words of new benchmark data in 8 low-resource African languages.<n>Our benchmarks are translations of Winogrande and three sections of MMLU: college medicine, clinical knowledge, and virology.<n>Using the benchmarks translated, we report previously unknown performance gaps between state-of-the-art (SOTA) LLMs in English and African languages.
  arXiv  Detail & Related papers  (2024-12-16T23:50:21Z)
• SciRIFF: A Resource to Enhance Language Model Instruction-Following over Scientific Literature [97.31347312130119]
  SciRIFF (Scientific Resource for Instruction-Following and Finetuning) is a dataset of 137K instruction-following instances for training and evaluation, covering 54 tasks.<n>These tasks span five core scientific literature understanding capabilities: information extraction, summarization, question answering, claim verification, and classification.<n> SciRIFF is unique in being entirely expert-written, high-quality instruction-following dataset for extracting and synthesizing information from research literature across diverse scientific fields.
  arXiv  Detail & Related papers  (2024-06-10T21:22:08Z)
• Baichuan 2: Open Large-scale Language Models [51.34140526283222]
  We present Baichuan 2, a series of large-scale multilingual language models containing 7 billion and 13 billion parameters, trained from scratch, on 2.6 trillion tokens.<n>Baichuan 2 matches or outperforms other open-source models of similar size on public benchmarks like MMLU, CMMLU, GSM8K, and HumanEval.
  arXiv  Detail & Related papers  (2023-09-19T04:13:22Z)
• MasakhaNER 2.0: Africa-centric Transfer Learning for Named Entity Recognition [55.95128479289923]
  African languages are spoken by over a billion people, but are underrepresented in NLP research and development. We create the largest human-annotated NER dataset for 20 African languages. We show that choosing the best transfer language improves zero-shot F1 scores by an average of 14 points.
  arXiv  Detail & Related papers  (2022-10-22T08:53:14Z)
• SciNLI: A Corpus for Natural Language Inference on Scientific Text [47.293189105900524]
  We introduce SciNLI, a large dataset for NLI that captures the formality in scientific text. Our best performing model with XLNet achieves a Macro F1 score of only 78.18% and an accuracy of 78.23%.
  arXiv  Detail & Related papers  (2022-03-13T18:23:37Z)
• AfroMT: Pretraining Strategies and Reproducible Benchmarks for Translation of 8 African Languages [94.75849612191546]
  AfroMT is a standardized, clean, and reproducible machine translation benchmark for eight widely spoken African languages. We develop a suite of analysis tools for system diagnosis taking into account the unique properties of these languages. We demonstrate significant improvements when pretraining on 11 languages, with gains of up to 2 BLEU points over strong baselines.
  arXiv  Detail & Related papers  (2021-09-10T07:45:21Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.