Zarma SpellChecker

This study presents a comparative analysis of spellchecking methods for Zarma, a low-resource Nilo-Saharan language. We examine three distinct approaches for Grammatical Error Correction (GEC): traditional rule-based methods, the novel application of Large Language Models (LLMs), and the use of Machine Translation (MT) models. Through rigorous evaluations, we compare the strengths and limitations of each method, assessing their effectiveness in identifying and correcting errors in Zarma text. Our findings highlight the promising potential of both LLMs and MT models to significantly enhance spellchecking capabilities for low-resource languages---paving the way for the development of more inclusive and robust Natural Language Processing (NLP) tools for African languages.