@inproceedings{nwafor-nguyen-2025-fostering,
title = "Fostering Digital Inclusion for Low-Resource {N}igerian Languages: A Case Study of {I}gbo and {N}igerian {P}idgin",
author = "Nwafor, Ebelechukwu and
Nguyen, Minh Phuc",
editor = "Ojha, Atul Kr. and
Liu, Chao-hong and
Vylomova, Ekaterina and
Pirinen, Flammie and
Washington, Jonathan and
Oco, Nathaniel and
Zhao, Xiaobing",
booktitle = "Proceedings of the Eighth Workshop on Technologies for Machine Translation of Low-Resource Languages (LoResMT 2025)",
month = may,
year = "2025",
address = "Albuquerque, New Mexico, U.S.A.",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.loresmt-1.6/",
doi = "10.18653/v1/2025.loresmt-1.6",
pages = "44--53",
ISBN = "979-8-89176-230-5",
abstract = "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."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nwafor-nguyen-2025-fostering">
<titleInfo>
<title>Fostering Digital Inclusion for Low-Resource Nigerian Languages: A Case Study of Igbo and Nigerian Pidgin</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ebelechukwu</namePart>
<namePart type="family">Nwafor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Minh</namePart>
<namePart type="given">Phuc</namePart>
<namePart type="family">Nguyen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Eighth Workshop on Technologies for Machine Translation of Low-Resource Languages (LoResMT 2025)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Atul</namePart>
<namePart type="given">Kr.</namePart>
<namePart type="family">Ojha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chao-hong</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Vylomova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Flammie</namePart>
<namePart type="family">Pirinen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jonathan</namePart>
<namePart type="family">Washington</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nathaniel</namePart>
<namePart type="family">Oco</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaobing</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Albuquerque, New Mexico, U.S.A.</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-230-5</identifier>
</relatedItem>
<abstract>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.</abstract>
<identifier type="citekey">nwafor-nguyen-2025-fostering</identifier>
<identifier type="doi">10.18653/v1/2025.loresmt-1.6</identifier>
<location>
<url>https://aclanthology.org/2025.loresmt-1.6/</url>
</location>
<part>
<date>2025-05</date>
<extent unit="page">
<start>44</start>
<end>53</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Fostering Digital Inclusion for Low-Resource Nigerian Languages: A Case Study of Igbo and Nigerian Pidgin
%A Nwafor, Ebelechukwu
%A Nguyen, Minh Phuc
%Y Ojha, Atul Kr.
%Y Liu, Chao-hong
%Y Vylomova, Ekaterina
%Y Pirinen, Flammie
%Y Washington, Jonathan
%Y Oco, Nathaniel
%Y Zhao, Xiaobing
%S Proceedings of the Eighth Workshop on Technologies for Machine Translation of Low-Resource Languages (LoResMT 2025)
%D 2025
%8 May
%I Association for Computational Linguistics
%C Albuquerque, New Mexico, U.S.A.
%@ 979-8-89176-230-5
%F nwafor-nguyen-2025-fostering
%X 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.
%R 10.18653/v1/2025.loresmt-1.6
%U https://aclanthology.org/2025.loresmt-1.6/
%U https://doi.org/10.18653/v1/2025.loresmt-1.6
%P 44-53
Markdown (Informal)
[Fostering Digital Inclusion for Low-Resource Nigerian Languages: A Case Study of Igbo and Nigerian Pidgin](https://aclanthology.org/2025.loresmt-1.6/) (Nwafor & Nguyen, LoResMT 2025)
ACL