@inproceedings{qwaider-etal-2025-enhancing,
title = "Enhancing {A}rabic Automated Essay Scoring with Synthetic Data and Error Injection",
author = "Qwaider, Chatrine and
Alhafni, Bashar and
Chirkunov, Kirill and
Habash, Nizar and
Briscoe, Ted",
editor = {Kochmar, Ekaterina and
Alhafni, Bashar and
Bexte, Marie and
Burstein, Jill and
Horbach, Andrea and
Laarmann-Quante, Ronja and
Tack, Ana{\"i}s and
Yaneva, Victoria and
Yuan, Zheng},
booktitle = "Proceedings of the 20th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2025)",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.bea-1.40/",
doi = "10.18653/v1/2025.bea-1.40",
pages = "549--563",
ISBN = "979-8-89176-270-1",
abstract = "Automated Essay Scoring (AES) plays a crucial role in assessing language learners' writingquality, reducing grading workload, and providing real-time feedback. The lack of annotatedessay datasets inhibits the development of Arabic AES systems. This paper leverages LargeLanguage Models (LLMs) and Transformermodels to generate synthetic Arabic essays forAES. We prompt an LLM to generate essaysacross the Common European Framework ofReference (CEFR) proficiency levels and introduce and compare two approaches to errorinjection. We create a dataset of 3,040 annotated essays with errors injected using our twomethods. Additionally, we develop a BERTbased Arabic AES system calibrated to CEFRlevels. Our experimental results demonstratethe effectiveness of our synthetic dataset in improving Arabic AES performance. We makeour code and data publicly available"
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="qwaider-etal-2025-enhancing">
<titleInfo>
<title>Enhancing Arabic Automated Essay Scoring with Synthetic Data and Error Injection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chatrine</namePart>
<namePart type="family">Qwaider</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bashar</namePart>
<namePart type="family">Alhafni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kirill</namePart>
<namePart type="family">Chirkunov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nizar</namePart>
<namePart type="family">Habash</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ted</namePart>
<namePart type="family">Briscoe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 20th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2025)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Kochmar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bashar</namePart>
<namePart type="family">Alhafni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marie</namePart>
<namePart type="family">Bexte</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jill</namePart>
<namePart type="family">Burstein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrea</namePart>
<namePart type="family">Horbach</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ronja</namePart>
<namePart type="family">Laarmann-Quante</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anaïs</namePart>
<namePart type="family">Tack</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Victoria</namePart>
<namePart type="family">Yaneva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zheng</namePart>
<namePart type="family">Yuan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-270-1</identifier>
</relatedItem>
<abstract>Automated Essay Scoring (AES) plays a crucial role in assessing language learners’ writingquality, reducing grading workload, and providing real-time feedback. The lack of annotatedessay datasets inhibits the development of Arabic AES systems. This paper leverages LargeLanguage Models (LLMs) and Transformermodels to generate synthetic Arabic essays forAES. We prompt an LLM to generate essaysacross the Common European Framework ofReference (CEFR) proficiency levels and introduce and compare two approaches to errorinjection. We create a dataset of 3,040 annotated essays with errors injected using our twomethods. Additionally, we develop a BERTbased Arabic AES system calibrated to CEFRlevels. Our experimental results demonstratethe effectiveness of our synthetic dataset in improving Arabic AES performance. We makeour code and data publicly available</abstract>
<identifier type="citekey">qwaider-etal-2025-enhancing</identifier>
<identifier type="doi">10.18653/v1/2025.bea-1.40</identifier>
<location>
<url>https://aclanthology.org/2025.bea-1.40/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>549</start>
<end>563</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Enhancing Arabic Automated Essay Scoring with Synthetic Data and Error Injection
%A Qwaider, Chatrine
%A Alhafni, Bashar
%A Chirkunov, Kirill
%A Habash, Nizar
%A Briscoe, Ted
%Y Kochmar, Ekaterina
%Y Alhafni, Bashar
%Y Bexte, Marie
%Y Burstein, Jill
%Y Horbach, Andrea
%Y Laarmann-Quante, Ronja
%Y Tack, Anaïs
%Y Yaneva, Victoria
%Y Yuan, Zheng
%S Proceedings of the 20th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2025)
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-270-1
%F qwaider-etal-2025-enhancing
%X Automated Essay Scoring (AES) plays a crucial role in assessing language learners’ writingquality, reducing grading workload, and providing real-time feedback. The lack of annotatedessay datasets inhibits the development of Arabic AES systems. This paper leverages LargeLanguage Models (LLMs) and Transformermodels to generate synthetic Arabic essays forAES. We prompt an LLM to generate essaysacross the Common European Framework ofReference (CEFR) proficiency levels and introduce and compare two approaches to errorinjection. We create a dataset of 3,040 annotated essays with errors injected using our twomethods. Additionally, we develop a BERTbased Arabic AES system calibrated to CEFRlevels. Our experimental results demonstratethe effectiveness of our synthetic dataset in improving Arabic AES performance. We makeour code and data publicly available
%R 10.18653/v1/2025.bea-1.40
%U https://aclanthology.org/2025.bea-1.40/
%U https://doi.org/10.18653/v1/2025.bea-1.40
%P 549-563
Markdown (Informal)
[Enhancing Arabic Automated Essay Scoring with Synthetic Data and Error Injection](https://aclanthology.org/2025.bea-1.40/) (Qwaider et al., BEA 2025)
ACL