@inproceedings{yousuf-etal-2026-dataset,
title = "A Dataset of {W}olof Ajami Manuscripts for {HTR} and {OCR}",
author = "Yousuf, Oreen and
Diagne, Elhadji Djibril and
H{\o}gel, Christian and
Megyesi, Beata and
Nivre, Joakim",
editor = "Piperidis, Stelios and
Bel, N{\'u}ria and
van den Heuvel, Henk and
Ide, Nancy and
Krek, Simon and
Toral, Antonio",
booktitle = "Proceedings of the Fifteenth Language Resources and Evaluation Conference",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "ELRA Language Resource Association",
url = "https://aclanthology.org/2026.lrec-1.253/",
doi = "10.63317/4pz98ojeeqpw",
pages = "3234--3239",
abstract = "We present the first ever dataset of manually segmented and transcribed Ajami manuscripts written in Wolof. The term Ajami refers to modified Arabic-script orthographies used to transcribe African languages. Handwritten text recognition (HTR) and optical character recognition (OCR) models for Arabic-script languages perform poorly on African languages written in Ajami orthographies because these languages are not represented in the pre-training data of the models. This leads to recognition models being unable to extract unique Arabic-script letters and ubiquitous diacritics used in African languages, and struggling to adapt to various calligraphy styles used across Africa. We release the following as an open-source dataset: an ALTO formatting of high-quality images of handwritten and printed, 20th{--}century Wolof manuscripts; manual segmentation (region and line); and manual transcriptions. We extend our contribution by evaluating several Arabic-script recognition models intended for historical manuscripts and find they produce character error rates (CER) of 61{--}81{\%}. Transcriptions produced by the evaluated recognition models, as well as a keyboard to transcribe Wolof Ajami manuscripts, are released as well. The digitally transcribed text in the dataset can also be utilized for various natural language processing (NLP) and historical linguistic tasks."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yousuf-etal-2026-dataset">
<titleInfo>
<title>A Dataset of Wolof Ajami Manuscripts for HTR and OCR</title>
</titleInfo>
<name type="personal">
<namePart type="given">Oreen</namePart>
<namePart type="family">Yousuf</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elhadji</namePart>
<namePart type="given">Djibril</namePart>
<namePart type="family">Diagne</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christian</namePart>
<namePart type="family">Høgel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Beata</namePart>
<namePart type="family">Megyesi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joakim</namePart>
<namePart type="family">Nivre</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Núria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Henk</namePart>
<namePart type="family">van den Heuvel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nancy</namePart>
<namePart type="family">Ide</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Krek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Toral</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resource Association</publisher>
<place>
<placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present the first ever dataset of manually segmented and transcribed Ajami manuscripts written in Wolof. The term Ajami refers to modified Arabic-script orthographies used to transcribe African languages. Handwritten text recognition (HTR) and optical character recognition (OCR) models for Arabic-script languages perform poorly on African languages written in Ajami orthographies because these languages are not represented in the pre-training data of the models. This leads to recognition models being unable to extract unique Arabic-script letters and ubiquitous diacritics used in African languages, and struggling to adapt to various calligraphy styles used across Africa. We release the following as an open-source dataset: an ALTO formatting of high-quality images of handwritten and printed, 20th–century Wolof manuscripts; manual segmentation (region and line); and manual transcriptions. We extend our contribution by evaluating several Arabic-script recognition models intended for historical manuscripts and find they produce character error rates (CER) of 61–81%. Transcriptions produced by the evaluated recognition models, as well as a keyboard to transcribe Wolof Ajami manuscripts, are released as well. The digitally transcribed text in the dataset can also be utilized for various natural language processing (NLP) and historical linguistic tasks.</abstract>
<identifier type="citekey">yousuf-etal-2026-dataset</identifier>
<identifier type="doi">10.63317/4pz98ojeeqpw</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.253/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>3234</start>
<end>3239</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Dataset of Wolof Ajami Manuscripts for HTR and OCR
%A Yousuf, Oreen
%A Diagne, Elhadji Djibril
%A Høgel, Christian
%A Megyesi, Beata
%A Nivre, Joakim
%Y Piperidis, Stelios
%Y Bel, Núria
%Y van den Heuvel, Henk
%Y Ide, Nancy
%Y Krek, Simon
%Y Toral, Antonio
%S Proceedings of the Fifteenth Language Resources and Evaluation Conference
%D 2026
%8 May
%I ELRA Language Resource Association
%C Palma de Mallorca, Spain
%F yousuf-etal-2026-dataset
%X We present the first ever dataset of manually segmented and transcribed Ajami manuscripts written in Wolof. The term Ajami refers to modified Arabic-script orthographies used to transcribe African languages. Handwritten text recognition (HTR) and optical character recognition (OCR) models for Arabic-script languages perform poorly on African languages written in Ajami orthographies because these languages are not represented in the pre-training data of the models. This leads to recognition models being unable to extract unique Arabic-script letters and ubiquitous diacritics used in African languages, and struggling to adapt to various calligraphy styles used across Africa. We release the following as an open-source dataset: an ALTO formatting of high-quality images of handwritten and printed, 20th–century Wolof manuscripts; manual segmentation (region and line); and manual transcriptions. We extend our contribution by evaluating several Arabic-script recognition models intended for historical manuscripts and find they produce character error rates (CER) of 61–81%. Transcriptions produced by the evaluated recognition models, as well as a keyboard to transcribe Wolof Ajami manuscripts, are released as well. The digitally transcribed text in the dataset can also be utilized for various natural language processing (NLP) and historical linguistic tasks.
%R 10.63317/4pz98ojeeqpw
%U https://aclanthology.org/2026.lrec-1.253/
%U https://doi.org/10.63317/4pz98ojeeqpw
%P 3234-3239
Markdown (Informal)
[A Dataset of Wolof Ajami Manuscripts for HTR and OCR](https://aclanthology.org/2026.lrec-1.253/) (Yousuf et al., LREC 2026)
ACL
- Oreen Yousuf, Elhadji Djibril Diagne, Christian Høgel, Beata Megyesi, and Joakim Nivre. 2026. A Dataset of Wolof Ajami Manuscripts for HTR and OCR. In Proceedings of the Fifteenth Language Resources and Evaluation Conference, pages 3234–3239, Palma de Mallorca, Spain. ELRA Language Resource Association.