@inproceedings{shams-etal-2026-scripting,
title = "Scripting History: A Diachronic {U}rdu Text and Image Corpus from the 18{T}h to 19{T}h Centuries",
author = "Shams, Sana and
Rauf, Sahar and
Mustafa, Asad and
Javed, Muhammad Zeeshan and
Akram, Qurat-ul-Ain and
Hussain, Sarmad and
Butt, Miriam",
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-1.127/",
doi = "10.63317/48tdw3hsxp47",
pages = "1622--1632",
abstract = "This paper presents the Diachronic Urdu Text and Image Corpus, a one-million-word resource covering Urdu{'}s development across the 18th and 19th centuries. The corpus is compiled from 328 printed books published between 1800 and 1950, representing a diverse range of genres, authors, and publishers. A 140,000-word sub-corpus has been manually annotated with Urdu part-of-speech tags to facilitate linguistic and computational analysis. The dataset enables systematic investigation of historical changes in Urdu orthography, morphology, and syntax, providing new insights into the language{'}s history and standardization. To preserve the original printed form, each text is paired with its corresponding page image, creating the first multimodal diachronic corpus for Urdu. The paper outlines the corpus compilation pipeline, digitization workflow, text-image alignment, and annotation strategy designed to ensure accuracy, consistency, and authenticity. This multimodal Urdu diachronic corpus establishes a benchmark for research in computational linguistics, digital humanities, and South Asian language technology, supporting corpus-based exploration of Urdu{'}s linguistic history and cultural heritage."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shams-etal-2026-scripting">
<titleInfo>
<title>Scripting History: A Diachronic Urdu Text and Image Corpus from the 18Th to 19Th Centuries</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sana</namePart>
<namePart type="family">Shams</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sahar</namePart>
<namePart type="family">Rauf</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asad</namePart>
<namePart type="family">Mustafa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Muhammad</namePart>
<namePart type="given">Zeeshan</namePart>
<namePart type="family">Javed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qurat-ul-Ain</namePart>
<namePart type="family">Akram</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sarmad</namePart>
<namePart type="family">Hussain</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Miriam</namePart>
<namePart type="family">Butt</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>This paper presents the Diachronic Urdu Text and Image Corpus, a one-million-word resource covering Urdu’s development across the 18th and 19th centuries. The corpus is compiled from 328 printed books published between 1800 and 1950, representing a diverse range of genres, authors, and publishers. A 140,000-word sub-corpus has been manually annotated with Urdu part-of-speech tags to facilitate linguistic and computational analysis. The dataset enables systematic investigation of historical changes in Urdu orthography, morphology, and syntax, providing new insights into the language’s history and standardization. To preserve the original printed form, each text is paired with its corresponding page image, creating the first multimodal diachronic corpus for Urdu. The paper outlines the corpus compilation pipeline, digitization workflow, text-image alignment, and annotation strategy designed to ensure accuracy, consistency, and authenticity. This multimodal Urdu diachronic corpus establishes a benchmark for research in computational linguistics, digital humanities, and South Asian language technology, supporting corpus-based exploration of Urdu’s linguistic history and cultural heritage.</abstract>
<identifier type="citekey">shams-etal-2026-scripting</identifier>
<identifier type="doi">10.63317/48tdw3hsxp47</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.127/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>1622</start>
<end>1632</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Scripting History: A Diachronic Urdu Text and Image Corpus from the 18Th to 19Th Centuries
%A Shams, Sana
%A Rauf, Sahar
%A Mustafa, Asad
%A Javed, Muhammad Zeeshan
%A Akram, Qurat-ul-Ain
%A Hussain, Sarmad
%A Butt, Miriam
%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 shams-etal-2026-scripting
%X This paper presents the Diachronic Urdu Text and Image Corpus, a one-million-word resource covering Urdu’s development across the 18th and 19th centuries. The corpus is compiled from 328 printed books published between 1800 and 1950, representing a diverse range of genres, authors, and publishers. A 140,000-word sub-corpus has been manually annotated with Urdu part-of-speech tags to facilitate linguistic and computational analysis. The dataset enables systematic investigation of historical changes in Urdu orthography, morphology, and syntax, providing new insights into the language’s history and standardization. To preserve the original printed form, each text is paired with its corresponding page image, creating the first multimodal diachronic corpus for Urdu. The paper outlines the corpus compilation pipeline, digitization workflow, text-image alignment, and annotation strategy designed to ensure accuracy, consistency, and authenticity. This multimodal Urdu diachronic corpus establishes a benchmark for research in computational linguistics, digital humanities, and South Asian language technology, supporting corpus-based exploration of Urdu’s linguistic history and cultural heritage.
%R 10.63317/48tdw3hsxp47
%U https://aclanthology.org/2026.lrec-1.127/
%U https://doi.org/10.63317/48tdw3hsxp47
%P 1622-1632
Markdown (Informal)
[Scripting History: A Diachronic Urdu Text and Image Corpus from the 18Th to 19Th Centuries](https://aclanthology.org/2026.lrec-1.127/) (Shams et al., LREC 2026)
ACL