Building a Functional Machine Translation Corpus for Kpelle

AbstractIn this paper, we introduce the first publicly available English-Kpelle dataset for machine translation, comprising over 2,000 sentence pairs drawn from everyday communication, religious texts, and educational materials. By fine-tuning Metas No Language Left Behind (NLLB) model on two versions of the dataset, we achieved BLEU scores of up to 30 in the Kpelle-to-English direction, demonstrating the benefits of data augmentation. Our findings align with NLLB-200 benchmarks on other African languages, underscoring Kpelles potential for competitive performance despite its low-resource status. Beyond machine translation, this dataset enables broader NLP tasks, including speech recognition and language modeling. We conclude with a roadmap for future dataset expansion, emphasizing orthographic consistency, community-driven validation, and interdisciplinary collaboration to advance inclusive language technology development for Kpelle and other low-resourced Mande languages.