@inproceedings{ahad-etal-2026-corpora,
title = "Corpora Generation for {U}rdu Grammatical Error Correction",
author = "Ahad, Syed and
Ezzi, Burhanuddin Aliasghar and
Hussain, Muhammad Arsalan and
Kumar, Sandesh and
Samad, Abdul",
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.2156/",
pages = "43428--43444",
ISBN = "979-8-89176-395-1",
abstract = "Grammatical Error Correction (GEC) for Urdu remains an under-researched area due to the lack of annotated datasets. This paper addresses the challenge of generating a robust corpus for fine-tuning deep learning models aimed at Urdu GEC. We propose a method for synthesizing a large dataset by collecting errors from the Urdu WikiEdits history, learning from them, and inserting similar errors in grammatically correct sentences to generate incorrect sentences with grammatical errors, hence creating a pair of grammatically correct and incorrect sentences. We introduce UrduGEC-Synthetic, a synthetically generated dataset produced through this pipeline. Furthermore, we introduce UrduGEC-Gold, a Gold Dataset by extracting errors from exam copies of students. Finally, we also fine-tuned various models on UrduGEC-Synthetic and evaluated them against UrduGEC-Gold to show the quality of synthetic data generation."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ahad-etal-2026-corpora">
<titleInfo>
<title>Corpora Generation for Urdu Grammatical Error Correction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Syed</namePart>
<namePart type="family">Ahad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Burhanuddin</namePart>
<namePart type="given">Aliasghar</namePart>
<namePart type="family">Ezzi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Muhammad</namePart>
<namePart type="given">Arsalan</namePart>
<namePart type="family">Hussain</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sandesh</namePart>
<namePart type="family">Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abdul</namePart>
<namePart type="family">Samad</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>Grammatical Error Correction (GEC) for Urdu remains an under-researched area due to the lack of annotated datasets. This paper addresses the challenge of generating a robust corpus for fine-tuning deep learning models aimed at Urdu GEC. We propose a method for synthesizing a large dataset by collecting errors from the Urdu WikiEdits history, learning from them, and inserting similar errors in grammatically correct sentences to generate incorrect sentences with grammatical errors, hence creating a pair of grammatically correct and incorrect sentences. We introduce UrduGEC-Synthetic, a synthetically generated dataset produced through this pipeline. Furthermore, we introduce UrduGEC-Gold, a Gold Dataset by extracting errors from exam copies of students. Finally, we also fine-tuned various models on UrduGEC-Synthetic and evaluated them against UrduGEC-Gold to show the quality of synthetic data generation.</abstract>
<identifier type="citekey">ahad-etal-2026-corpora</identifier>
<location>
<url>https://aclanthology.org/2026.findings-acl.2156/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>43428</start>
<end>43444</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Corpora Generation for Urdu Grammatical Error Correction
%A Ahad, Syed
%A Ezzi, Burhanuddin Aliasghar
%A Hussain, Muhammad Arsalan
%A Kumar, Sandesh
%A Samad, Abdul
%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 ahad-etal-2026-corpora
%X Grammatical Error Correction (GEC) for Urdu remains an under-researched area due to the lack of annotated datasets. This paper addresses the challenge of generating a robust corpus for fine-tuning deep learning models aimed at Urdu GEC. We propose a method for synthesizing a large dataset by collecting errors from the Urdu WikiEdits history, learning from them, and inserting similar errors in grammatically correct sentences to generate incorrect sentences with grammatical errors, hence creating a pair of grammatically correct and incorrect sentences. We introduce UrduGEC-Synthetic, a synthetically generated dataset produced through this pipeline. Furthermore, we introduce UrduGEC-Gold, a Gold Dataset by extracting errors from exam copies of students. Finally, we also fine-tuned various models on UrduGEC-Synthetic and evaluated them against UrduGEC-Gold to show the quality of synthetic data generation.
%U https://aclanthology.org/2026.findings-acl.2156/
%P 43428-43444
Markdown (Informal)
[Corpora Generation for Urdu Grammatical Error Correction](https://aclanthology.org/2026.findings-acl.2156/) (Ahad et al., Findings 2026)
ACL
- Syed Ahad, Burhanuddin Aliasghar Ezzi, Muhammad Arsalan Hussain, Sandesh Kumar, and Abdul Samad. 2026. Corpora Generation for Urdu Grammatical Error Correction. In Findings of the Association for Computational Linguistics: ACL 2026, pages 43428–43444, San Diego, California, United States. Association for Computational Linguistics.