@inproceedings{stanislas-rocksane-compaore-etal-2026-neural,
title = "Neural Machine Translation for {F}rench{--}Moor{\'e}: Adapting Large Language Models to Low-Resource Languages",
author = "Stanislas Rocksane COMPAORE, Walker and
Ouattara, Maimouna and
Kafando, Rodrique and
Bissyand{\'e}, Tegawend{\'e} F. and
Kabore, Abdoul Kader and
Sabane, Aminata",
editor = "Hettiarachchi, Hansi and
Ranasinghe, Tharindu and
Plum, Alistair and
Rayson, Paul and
Mitkov, Ruslan and
Gaber, Mohamed and
Premasiri, Damith and
Tan, Fiona Anting and
Uyangodage, Lasitha",
booktitle = "Proceedings of the Second Workshop on Language Models for Low-Resource Languages ({L}o{R}es{LM} 2026)",
month = mar,
year = "2026",
address = "Rabat, Morocco",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.loreslm-1.53/",
pages = "615--622",
ISBN = "979-8-89176-377-7",
abstract = "This work focuses on neural machine translation between French and Moor{\'e}, leveraging the capabilities of Large Language Models (LLMs) in a low-resource language context. Moor{\'e} is a local language widely spoken in Burkina Faso but remains underrepresented in digital resources. Alongside Moor{\'e}, French, now a working language, remains widely used in administration, education, justice, etc. The coexistence of these two languages creates a growing demand for effective translation tools. However, Moor{\'e}, like many low-resource languages, poses significant challenges for machine translation due to the scarcity of parallel corpora and its complex morphology.The main objective of this work is to adapt LLMs for French{--}Moor{\'e} translation. Three pre-trained models were selected: No Language Left Behind (NLLB-200), mBART50, and AfroLM. A corpus of approximately 83,000 validated sentence pairs was compiled from an initial collection of 97,060 pairs through pre-processing, semantic filtering, and human evaluation. Specific adaptations to tokenizers and model architectures were applied to improve translation quality.The results show that the fine-tuned NLLB model outperforms the others, highlighting the importance of native language support. mBART50 achieves comparable performance after fine-tuning, while AfroLM remains less effective. Despite existing limitations, this study demonstrates the potential of fine-tuned LLMs for African low-resource languages."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="stanislas-rocksane-compaore-etal-2026-neural">
<titleInfo>
<title>Neural Machine Translation for French–Mooré: Adapting Large Language Models to Low-Resource Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Walker</namePart>
<namePart type="family">Stanislas Rocksane COMPAORE</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maimouna</namePart>
<namePart type="family">Ouattara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rodrique</namePart>
<namePart type="family">Kafando</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tegawendé</namePart>
<namePart type="given">F</namePart>
<namePart type="family">Bissyandé</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abdoul</namePart>
<namePart type="given">Kader</namePart>
<namePart type="family">Kabore</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aminata</namePart>
<namePart type="family">Sabane</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 Second Workshop on Language Models for Low-Resource Languages (LoResLM 2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hansi</namePart>
<namePart type="family">Hettiarachchi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tharindu</namePart>
<namePart type="family">Ranasinghe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alistair</namePart>
<namePart type="family">Plum</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paul</namePart>
<namePart type="family">Rayson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruslan</namePart>
<namePart type="family">Mitkov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohamed</namePart>
<namePart type="family">Gaber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Damith</namePart>
<namePart type="family">Premasiri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fiona</namePart>
<namePart type="given">Anting</namePart>
<namePart type="family">Tan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lasitha</namePart>
<namePart type="family">Uyangodage</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">979-8-89176-377-7</identifier>
</relatedItem>
<abstract>This work focuses on neural machine translation between French and Mooré, leveraging the capabilities of Large Language Models (LLMs) in a low-resource language context. Mooré is a local language widely spoken in Burkina Faso but remains underrepresented in digital resources. Alongside Mooré, French, now a working language, remains widely used in administration, education, justice, etc. The coexistence of these two languages creates a growing demand for effective translation tools. However, Mooré, like many low-resource languages, poses significant challenges for machine translation due to the scarcity of parallel corpora and its complex morphology.The main objective of this work is to adapt LLMs for French–Mooré translation. Three pre-trained models were selected: No Language Left Behind (NLLB-200), mBART50, and AfroLM. A corpus of approximately 83,000 validated sentence pairs was compiled from an initial collection of 97,060 pairs through pre-processing, semantic filtering, and human evaluation. Specific adaptations to tokenizers and model architectures were applied to improve translation quality.The results show that the fine-tuned NLLB model outperforms the others, highlighting the importance of native language support. mBART50 achieves comparable performance after fine-tuning, while AfroLM remains less effective. Despite existing limitations, this study demonstrates the potential of fine-tuned LLMs for African low-resource languages.</abstract>
<identifier type="citekey">stanislas-rocksane-compaore-etal-2026-neural</identifier>
<location>
<url>https://aclanthology.org/2026.loreslm-1.53/</url>
</location>
<part>
<date>2026-03</date>
<extent unit="page">
<start>615</start>
<end>622</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Neural Machine Translation for French–Mooré: Adapting Large Language Models to Low-Resource Languages
%A Stanislas Rocksane COMPAORE, Walker
%A Ouattara, Maimouna
%A Kafando, Rodrique
%A Bissyandé, Tegawendé F.
%A Kabore, Abdoul Kader
%A Sabane, Aminata
%Y Hettiarachchi, Hansi
%Y Ranasinghe, Tharindu
%Y Plum, Alistair
%Y Rayson, Paul
%Y Mitkov, Ruslan
%Y Gaber, Mohamed
%Y Premasiri, Damith
%Y Tan, Fiona Anting
%Y Uyangodage, Lasitha
%S Proceedings of the Second Workshop on Language Models for Low-Resource Languages (LoResLM 2026)
%D 2026
%8 March
%I Association for Computational Linguistics
%C Rabat, Morocco
%@ 979-8-89176-377-7
%F stanislas-rocksane-compaore-etal-2026-neural
%X This work focuses on neural machine translation between French and Mooré, leveraging the capabilities of Large Language Models (LLMs) in a low-resource language context. Mooré is a local language widely spoken in Burkina Faso but remains underrepresented in digital resources. Alongside Mooré, French, now a working language, remains widely used in administration, education, justice, etc. The coexistence of these two languages creates a growing demand for effective translation tools. However, Mooré, like many low-resource languages, poses significant challenges for machine translation due to the scarcity of parallel corpora and its complex morphology.The main objective of this work is to adapt LLMs for French–Mooré translation. Three pre-trained models were selected: No Language Left Behind (NLLB-200), mBART50, and AfroLM. A corpus of approximately 83,000 validated sentence pairs was compiled from an initial collection of 97,060 pairs through pre-processing, semantic filtering, and human evaluation. Specific adaptations to tokenizers and model architectures were applied to improve translation quality.The results show that the fine-tuned NLLB model outperforms the others, highlighting the importance of native language support. mBART50 achieves comparable performance after fine-tuning, while AfroLM remains less effective. Despite existing limitations, this study demonstrates the potential of fine-tuned LLMs for African low-resource languages.
%U https://aclanthology.org/2026.loreslm-1.53/
%P 615-622
Markdown (Informal)
[Neural Machine Translation for French–Mooré: Adapting Large Language Models to Low-Resource Languages](https://aclanthology.org/2026.loreslm-1.53/) (Stanislas Rocksane COMPAORE et al., LoResLM 2026)
ACL