@inproceedings{edet-etal-2026-developing,
title = "Developing an {E}nglish{--}{E}fik Corpus and Machine Translation System for Digitization Inclusion",
author = "Edet, Offiong Bassey and
Awak, Mbuotidem and
Oyo-Ita, Emmanuel Ubene and
Nyong, Benjamin Okon and
Bassey, Ita Etim",
editor = "Chimoto, Everlyn Asiko and
Lignos, Constantine and
Muhammad, Shamsuddeen and
Abdulmumin, Idris and
Siro, Clemencia and
Adelani, David Ifeoluwa",
booktitle = "Proceedings of the 7th Workshop on {A}frican Natural Language Processing ({A}frica{NLP} 2026)",
month = mar,
year = "2026",
address = "Rabat, Morocco",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.africanlp-main.6/",
pages = "56--63",
ISBN = "979-8-89176-364-7",
abstract = "Low-resource languages serve as invaluable repositories of human history, preserving cultural and intellectual diversity. Despite their significance, they remain largely absent from modern natural language processing systems. While progress has been made for widely spoken African languages such as Swahili, Yoruba, and Amharic, smaller indigenous languages like Efik continue to be underrepresented in machine translation research. This study evaluates the effectiveness of state-of-the-art multilingual neural machine translation models for English{--}Efik translation, leveraging a small-scale, community-curated parallel corpus of $N = 13{,}865$ sentence pairs. We fine-tuned both the mT5 multilingual model and the NLLB-200 model on this dataset. NLLB-200 outperformed mT5, achieving BLEU scores of 26.64 for English{--}Efik and 31.21 for Efik{--}English, with corresponding chrF scores of 51.04 and 47.92, indicating improved fluency and semantic fidelity. Our findings demonstrate the feasibility of developing practical machine translation tools for low-resource languages and highlight the importance of inclusive data practices and culturally grounded evaluation in advancing equitable NLP."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="edet-etal-2026-developing">
<titleInfo>
<title>Developing an English–Efik Corpus and Machine Translation System for Digitization Inclusion</title>
</titleInfo>
<name type="personal">
<namePart type="given">Offiong</namePart>
<namePart type="given">Bassey</namePart>
<namePart type="family">Edet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mbuotidem</namePart>
<namePart type="family">Awak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Emmanuel</namePart>
<namePart type="given">Ubene</namePart>
<namePart type="family">Oyo-Ita</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Benjamin</namePart>
<namePart type="given">Okon</namePart>
<namePart type="family">Nyong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ita</namePart>
<namePart type="given">Etim</namePart>
<namePart type="family">Bassey</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 7th Workshop on African Natural Language Processing (AfricaNLP 2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Everlyn</namePart>
<namePart type="given">Asiko</namePart>
<namePart type="family">Chimoto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Constantine</namePart>
<namePart type="family">Lignos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shamsuddeen</namePart>
<namePart type="family">Muhammad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Idris</namePart>
<namePart type="family">Abdulmumin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Clemencia</namePart>
<namePart type="family">Siro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="given">Ifeoluwa</namePart>
<namePart type="family">Adelani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Rabat, Morocco</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-364-7</identifier>
</relatedItem>
<abstract>Low-resource languages serve as invaluable repositories of human history, preserving cultural and intellectual diversity. Despite their significance, they remain largely absent from modern natural language processing systems. While progress has been made for widely spoken African languages such as Swahili, Yoruba, and Amharic, smaller indigenous languages like Efik continue to be underrepresented in machine translation research. This study evaluates the effectiveness of state-of-the-art multilingual neural machine translation models for English–Efik translation, leveraging a small-scale, community-curated parallel corpus of N = 13,865 sentence pairs. We fine-tuned both the mT5 multilingual model and the NLLB-200 model on this dataset. NLLB-200 outperformed mT5, achieving BLEU scores of 26.64 for English–Efik and 31.21 for Efik–English, with corresponding chrF scores of 51.04 and 47.92, indicating improved fluency and semantic fidelity. Our findings demonstrate the feasibility of developing practical machine translation tools for low-resource languages and highlight the importance of inclusive data practices and culturally grounded evaluation in advancing equitable NLP.</abstract>
<identifier type="citekey">edet-etal-2026-developing</identifier>
<location>
<url>https://aclanthology.org/2026.africanlp-main.6/</url>
</location>
<part>
<date>2026-03</date>
<extent unit="page">
<start>56</start>
<end>63</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Developing an English–Efik Corpus and Machine Translation System for Digitization Inclusion
%A Edet, Offiong Bassey
%A Awak, Mbuotidem
%A Oyo-Ita, Emmanuel Ubene
%A Nyong, Benjamin Okon
%A Bassey, Ita Etim
%Y Chimoto, Everlyn Asiko
%Y Lignos, Constantine
%Y Muhammad, Shamsuddeen
%Y Abdulmumin, Idris
%Y Siro, Clemencia
%Y Adelani, David Ifeoluwa
%S Proceedings of the 7th Workshop on African Natural Language Processing (AfricaNLP 2026)
%D 2026
%8 March
%I Association for Computational Linguistics
%C Rabat, Morocco
%@ 979-8-89176-364-7
%F edet-etal-2026-developing
%X Low-resource languages serve as invaluable repositories of human history, preserving cultural and intellectual diversity. Despite their significance, they remain largely absent from modern natural language processing systems. While progress has been made for widely spoken African languages such as Swahili, Yoruba, and Amharic, smaller indigenous languages like Efik continue to be underrepresented in machine translation research. This study evaluates the effectiveness of state-of-the-art multilingual neural machine translation models for English–Efik translation, leveraging a small-scale, community-curated parallel corpus of N = 13,865 sentence pairs. We fine-tuned both the mT5 multilingual model and the NLLB-200 model on this dataset. NLLB-200 outperformed mT5, achieving BLEU scores of 26.64 for English–Efik and 31.21 for Efik–English, with corresponding chrF scores of 51.04 and 47.92, indicating improved fluency and semantic fidelity. Our findings demonstrate the feasibility of developing practical machine translation tools for low-resource languages and highlight the importance of inclusive data practices and culturally grounded evaluation in advancing equitable NLP.
%U https://aclanthology.org/2026.africanlp-main.6/
%P 56-63
Markdown (Informal)
[Developing an English–Efik Corpus and Machine Translation System for Digitization Inclusion](https://aclanthology.org/2026.africanlp-main.6/) (Edet et al., AfricaNLP 2026)
ACL