@inproceedings{bashendy-elsayed-2026-corruption,
title = "Corruption-Based Data Augmentation for {A}rabic Essay Scoring: A Preliminary Study on the Organization Trait",
author = "Bashendy, May Saed and
Elsayed, Tamer",
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-1.825/",
doi = "10.63317/5kt6mmyaumav",
pages = "10525--10531",
abstract = "Despite significant advances in Automated Essay Scoring (AES), progress in Arabic AES remains limited by the scarcity and imbalance of publicly available datasets. Manual curation of such data is labor-intensive and lacks scalability. To address this, we introduce COrE, a corruption-based data augmentation method that targets the organization trait of Arabic essays. COrE generates synthetic essays by intentionally disrupting the organization of well-written essays through controlled, distance-aware sentence swapping. Our experiments are conducted on TAQAE, a dataset of 620 essays across 4 distinct writing prompts. We evaluate the effectiveness of COrE using two widely-adopted pre-trained models: AraBERTv2 and CAMeLBERT-mix. Both models show improved performance with COrE, achieving gains of 9-17{\%} over the no-augmentation baseline. These results highlight the potential of trait-specific augmentation to address data scarcity and enhance AES performance for low-resource languages."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bashendy-elsayed-2026-corruption">
<titleInfo>
<title>Corruption-Based Data Augmentation for Arabic Essay Scoring: A Preliminary Study on the Organization Trait</title>
</titleInfo>
<name type="personal">
<namePart type="given">May</namePart>
<namePart type="given">Saed</namePart>
<namePart type="family">Bashendy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tamer</namePart>
<namePart type="family">Elsayed</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>Despite significant advances in Automated Essay Scoring (AES), progress in Arabic AES remains limited by the scarcity and imbalance of publicly available datasets. Manual curation of such data is labor-intensive and lacks scalability. To address this, we introduce COrE, a corruption-based data augmentation method that targets the organization trait of Arabic essays. COrE generates synthetic essays by intentionally disrupting the organization of well-written essays through controlled, distance-aware sentence swapping. Our experiments are conducted on TAQAE, a dataset of 620 essays across 4 distinct writing prompts. We evaluate the effectiveness of COrE using two widely-adopted pre-trained models: AraBERTv2 and CAMeLBERT-mix. Both models show improved performance with COrE, achieving gains of 9-17% over the no-augmentation baseline. These results highlight the potential of trait-specific augmentation to address data scarcity and enhance AES performance for low-resource languages.</abstract>
<identifier type="citekey">bashendy-elsayed-2026-corruption</identifier>
<identifier type="doi">10.63317/5kt6mmyaumav</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.825/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>10525</start>
<end>10531</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Corruption-Based Data Augmentation for Arabic Essay Scoring: A Preliminary Study on the Organization Trait
%A Bashendy, May Saed
%A Elsayed, Tamer
%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 bashendy-elsayed-2026-corruption
%X Despite significant advances in Automated Essay Scoring (AES), progress in Arabic AES remains limited by the scarcity and imbalance of publicly available datasets. Manual curation of such data is labor-intensive and lacks scalability. To address this, we introduce COrE, a corruption-based data augmentation method that targets the organization trait of Arabic essays. COrE generates synthetic essays by intentionally disrupting the organization of well-written essays through controlled, distance-aware sentence swapping. Our experiments are conducted on TAQAE, a dataset of 620 essays across 4 distinct writing prompts. We evaluate the effectiveness of COrE using two widely-adopted pre-trained models: AraBERTv2 and CAMeLBERT-mix. Both models show improved performance with COrE, achieving gains of 9-17% over the no-augmentation baseline. These results highlight the potential of trait-specific augmentation to address data scarcity and enhance AES performance for low-resource languages.
%R 10.63317/5kt6mmyaumav
%U https://aclanthology.org/2026.lrec-1.825/
%U https://doi.org/10.63317/5kt6mmyaumav
%P 10525-10531
Markdown (Informal)
[Corruption-Based Data Augmentation for Arabic Essay Scoring: A Preliminary Study on the Organization Trait](https://aclanthology.org/2026.lrec-1.825/) (Bashendy & Elsayed, LREC 2026)
ACL