@inproceedings{okafor-2025-multilingual,
    title = "Multilingual {NLP} for {A}frican Healthcare: Bias, Translation, and Explainability Challenges",
    author = "Okafor, Ugochi",
    editor = "Lignos, Constantine  and
      Abdulmumin, Idris  and
      Adelani, David",
    booktitle = "Proceedings of the Sixth Workshop on African Natural Language Processing (AfricaNLP 2025)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/acl25-workshop-ingestion/2025.africanlp-1.32/",
    pages = "221--229",
    ISBN = "979-8-89176-257-2",
    abstract = "Despite advances in multilingual natural language processing (NLP) and machine translation (MT), African languages remain underrepresented due to data scarcity, tokenisation inefficiencies, and bias in AI models. Large-scale systems such as Meta AIs No Language Left Behind (NLLB) and the Flores-200 benchmark have improved low-resource language support, yet critical gaps persist, particularly in healthcare, where accuracy and trust are essential.This study systematically reviews over 30 peer-reviewed papers, technical reports, and datasets to assess the effectiveness of existing multilingual NLP models, specifically Masakhane-MT, Masakhane-NER, and AfromT, in African healthcare contexts. The analysis focuses on four languages with available evaluation data: Swahili, Yoruba, Hausa, and Igbo.Findings show that while AI tools such as medical chatbots and disease surveillance systems demonstrate promise, current models face persistent challenges including domain adaptation failures, cultural and linguistic bias, and limited explainability. Use cases like Ubenwas infant cry analysis tool and multilingual health translation systems illustrate both potential and risk, especially where translation errors or opacity may impact clinical decisions.The paper highlights the need for ethically grounded, domain-specific NLP approaches that reflect Africas linguistic diversity. We recommend strategies to address dataset imbalance, reduce bias, and improve explainability, while also calling for increased computational infrastructure and local AI governance. These steps are critical to making AI-driven healthcare solutions equitable, transparent, and effective for Africas multilingual populations."
}