@inproceedings{cisse-2026-kumatigi,
title = "Kumatigi: Quality-Driven Data Augmentation for Low-Resource Machine Translation",
author = "Ciss{\'e}, Cheick Tidiani",
editor = "Liakata, Maria and
Moreira, Viviane P. and
Zhang, Jiajun and
Jurgens, David",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-acl.1223/",
doi = "10.18653/v1/2026.findings-acl.1223",
pages = "24433--24446",
ISBN = "979-8-89176-395-1",
abstract = "Neural machine translation for extremely low-resource languages faces compounding challenges: scarce parallel data, orthographic inconsistency, and absence of quality metadata for principled training. We present Kumatigi, a quality-annotated French-Bambara corpus combining systematic curation with data augmentation strategies tailored to Bambara. We provide 67k quality-scored pairs that enable targeted data filtering and address pervasive orthographic normalization issues in existing resources. Our dual-dataset generation framework strategically exploits round-trip translation, producing synthetic pairs for fluency reinforcement alongside back-translated pairs that preserve authentic vocabulary for coverage expansion. We further introduce linguistically-motivated augmentation techniques addressing Bambara{'}s orthographic variability, improving model robustness for real-world text. Experiments with LoRA-based fine-tuning demonstrate consistent improvements across automatic metrics, with our full system achieving up to +3{--}4 BLEU over strong baselines. Data generation and augmentation strategies contribute +1-2 BLEU beyond high-quality parallel data alone. Human evaluation by native speakers confirms these automatic improvements align with substantial gains in translation adequacy and fluency, with our best model approaching human reference translation quality. Our methodology provides a reproducible framework applicable to other under-resourced languages facing similar data challenges."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="cisse-2026-kumatigi">
<titleInfo>
<title>Kumatigi: Quality-Driven Data Augmentation for Low-Resource Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Cheick</namePart>
<namePart type="given">Tidiani</namePart>
<namePart type="family">Cissé</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Liakata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Viviane</namePart>
<namePart type="given">P</namePart>
<namePart type="family">Moreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiajun</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Jurgens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-395-1</identifier>
</relatedItem>
<abstract>Neural machine translation for extremely low-resource languages faces compounding challenges: scarce parallel data, orthographic inconsistency, and absence of quality metadata for principled training. We present Kumatigi, a quality-annotated French-Bambara corpus combining systematic curation with data augmentation strategies tailored to Bambara. We provide 67k quality-scored pairs that enable targeted data filtering and address pervasive orthographic normalization issues in existing resources. Our dual-dataset generation framework strategically exploits round-trip translation, producing synthetic pairs for fluency reinforcement alongside back-translated pairs that preserve authentic vocabulary for coverage expansion. We further introduce linguistically-motivated augmentation techniques addressing Bambara’s orthographic variability, improving model robustness for real-world text. Experiments with LoRA-based fine-tuning demonstrate consistent improvements across automatic metrics, with our full system achieving up to +3–4 BLEU over strong baselines. Data generation and augmentation strategies contribute +1-2 BLEU beyond high-quality parallel data alone. Human evaluation by native speakers confirms these automatic improvements align with substantial gains in translation adequacy and fluency, with our best model approaching human reference translation quality. Our methodology provides a reproducible framework applicable to other under-resourced languages facing similar data challenges.</abstract>
<identifier type="citekey">cisse-2026-kumatigi</identifier>
<identifier type="doi">10.18653/v1/2026.findings-acl.1223</identifier>
<location>
<url>https://aclanthology.org/2026.findings-acl.1223/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>24433</start>
<end>24446</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Kumatigi: Quality-Driven Data Augmentation for Low-Resource Machine Translation
%A Cissé, Cheick Tidiani
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Findings of the Association for Computational Linguistics: ACL 2026
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-395-1
%F cisse-2026-kumatigi
%X Neural machine translation for extremely low-resource languages faces compounding challenges: scarce parallel data, orthographic inconsistency, and absence of quality metadata for principled training. We present Kumatigi, a quality-annotated French-Bambara corpus combining systematic curation with data augmentation strategies tailored to Bambara. We provide 67k quality-scored pairs that enable targeted data filtering and address pervasive orthographic normalization issues in existing resources. Our dual-dataset generation framework strategically exploits round-trip translation, producing synthetic pairs for fluency reinforcement alongside back-translated pairs that preserve authentic vocabulary for coverage expansion. We further introduce linguistically-motivated augmentation techniques addressing Bambara’s orthographic variability, improving model robustness for real-world text. Experiments with LoRA-based fine-tuning demonstrate consistent improvements across automatic metrics, with our full system achieving up to +3–4 BLEU over strong baselines. Data generation and augmentation strategies contribute +1-2 BLEU beyond high-quality parallel data alone. Human evaluation by native speakers confirms these automatic improvements align with substantial gains in translation adequacy and fluency, with our best model approaching human reference translation quality. Our methodology provides a reproducible framework applicable to other under-resourced languages facing similar data challenges.
%R 10.18653/v1/2026.findings-acl.1223
%U https://aclanthology.org/2026.findings-acl.1223/
%U https://doi.org/10.18653/v1/2026.findings-acl.1223
%P 24433-24446
Markdown (Informal)
[Kumatigi: Quality-Driven Data Augmentation for Low-Resource Machine Translation](https://aclanthology.org/2026.findings-acl.1223/) (Cissé, Findings 2026)
ACL