Ibom NLP: A Step Toward Inclusive Natural Language Processing for Nigeria's Minority Languages

TL;DR

This paper introduces a new dataset for four Nigerian minority languages, extending NLP benchmarks and revealing current language models' poor performance on translation tasks, but some improvement in topic classification with few-shot learning.

Contribution

It provides the first NLP dataset for four Nigerian minority languages and extends existing benchmarks to include these languages, highlighting challenges in translation.

Findings

Current LLMs perform poorly on translation for these languages.

Few-shot learning improves topic classification accuracy.

The dataset enables inclusive NLP research for Nigeria's minority languages.

Abstract

Nigeria is the most populous country in Africa with a population of more than 200 million people. More than 500 languages are spoken in Nigeria and it is one of the most linguistically diverse countries in the world. Despite this, natural language processing (NLP) research has mostly focused on the following four languages: Hausa, Igbo, Nigerian-Pidgin, and Yoruba (i.e <1% of the languages spoken in Nigeria). This is in part due to the unavailability of textual data in these languages to train and apply NLP algorithms. In this work, we introduce ibom -- a dataset for machine translation and topic classification in four Coastal Nigerian languages from the Akwa Ibom State region: Anaang, Efik, Ibibio, and Oro. These languages are not represented in Google Translate or in major benchmarks such as Flores-200 or SIB-200. We focus on extending Flores-200 benchmark to these languages, and further align the translated texts with topic labels based on SIB-200 classification dataset. Our evaluation shows that current LLMs perform poorly on machine translation for these languages in both zero-and-few shot settings. However, we find the few-shot samples to steadily improve topic classification with more shots.