Current state-of-the-art large language models (LLMs) like GPT-4 perform exceptionally well in language translation tasks for high-resource languages, such as English, but often lack high accuracy results for low-resource African languages such as Igbo and Nigerian Pidgin, two native languages in Nigeria. This study addresses the need for Artificial Intelligence (AI) linguistic diversity by creating benchmark datasets for Igbo-English and Nigerian Pidgin-English language translation tasks. The dataset developed is curated from reputable online sources and meticulously annotated by crowd-sourced native-speaking human annotators. Using the datasets, we evaluate the translation abilities of GPT-based models alongside other state-of-the-art translation models specifically designed for low-resource languages. Our results demonstrate that current state-of-the-art models outperform GPT-based models in translation tasks. In addition, these datasets can significantly enhance LLM performance in these translation tasks, marking a step toward reducing linguistic bias and promoting more inclusive AI models.

Machine translation is an active area of research that has received a significant amount of attention over the past decade. With the advent of deep learning models, the translation of several languages has been performed with high accuracy and precision. In spite of the development in machine translation techniques, there is very limited work focused on translating low-resource African languages, particularly Nigerian languages. Nigeria is one of the most populous countries in Africa with diverse language and ethnic groups. In this paper, we survey the current state of the art of machine translation research on Nigerian languages with a major emphasis on neural machine translation techniques. We outline the limitations of research in machine translation on Nigerian languages and propose future directions in increasing research and participation.