@inproceedings{yoo-etal-2025-dress,
title = "{DRE}s{S}: Dataset for Rubric-based Essay Scoring on {EFL} Writing",
author = "Yoo, Haneul and
Han, Jieun and
Ahn, So-Yeon and
Oh, Alice",
editor = "Che, Wanxiang and
Nabende, Joyce and
Shutova, Ekaterina and
Pilehvar, Mohammad Taher",
booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.acl-long.659/",
doi = "10.18653/v1/2025.acl-long.659",
pages = "13439--13454",
ISBN = "979-8-89176-251-0",
abstract = "Automated essay scoring (AES) is a useful tool in English as a Foreign Language (EFL) writing education, offering real-time essay scores for students and instructors. However, previous AES models were trained on essays and scores irrelevant to the practical scenarios of EFL writing education and usually provided a single holistic score due to the lack of appropriate datasets. In this paper, we release DREsS, a large-scale, standard dataset for rubric-based automated essay scoring with 48.9K samples in total. DREsS comprises three sub-datasets: DREsS{\_}New, DREsS{\_}Std., and DREsS{\_}CASE. We collect DREsS{\_}New, a real-classroom dataset with 2.3K essays authored by EFL undergraduate students and scored by English education experts. We also standardize existing rubric-based essay scoring datasets as DREsS{\_}Std. We suggest CASE, a corruption-based augmentation strategy for essays, which generates 40.1K synthetic samples of DREsS{\_}CASE and improves the baseline results by 45.44{\%}. DREsS will enable further research to provide a more accurate and practical AES system for EFL writing education."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yoo-etal-2025-dress">
<titleInfo>
<title>DREsS: Dataset for Rubric-based Essay Scoring on EFL Writing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Haneul</namePart>
<namePart type="family">Yoo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jieun</namePart>
<namePart type="family">Han</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">So-Yeon</namePart>
<namePart type="family">Ahn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alice</namePart>
<namePart type="family">Oh</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 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wanxiang</namePart>
<namePart type="family">Che</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joyce</namePart>
<namePart type="family">Nabende</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Shutova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">Taher</namePart>
<namePart type="family">Pilehvar</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">979-8-89176-251-0</identifier>
</relatedItem>
<abstract>Automated essay scoring (AES) is a useful tool in English as a Foreign Language (EFL) writing education, offering real-time essay scores for students and instructors. However, previous AES models were trained on essays and scores irrelevant to the practical scenarios of EFL writing education and usually provided a single holistic score due to the lack of appropriate datasets. In this paper, we release DREsS, a large-scale, standard dataset for rubric-based automated essay scoring with 48.9K samples in total. DREsS comprises three sub-datasets: DREsS_New, DREsS_Std., and DREsS_CASE. We collect DREsS_New, a real-classroom dataset with 2.3K essays authored by EFL undergraduate students and scored by English education experts. We also standardize existing rubric-based essay scoring datasets as DREsS_Std. We suggest CASE, a corruption-based augmentation strategy for essays, which generates 40.1K synthetic samples of DREsS_CASE and improves the baseline results by 45.44%. DREsS will enable further research to provide a more accurate and practical AES system for EFL writing education.</abstract>
<identifier type="citekey">yoo-etal-2025-dress</identifier>
<identifier type="doi">10.18653/v1/2025.acl-long.659</identifier>
<location>
<url>https://aclanthology.org/2025.acl-long.659/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>13439</start>
<end>13454</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T DREsS: Dataset for Rubric-based Essay Scoring on EFL Writing
%A Yoo, Haneul
%A Han, Jieun
%A Ahn, So-Yeon
%A Oh, Alice
%Y Che, Wanxiang
%Y Nabende, Joyce
%Y Shutova, Ekaterina
%Y Pilehvar, Mohammad Taher
%S Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-251-0
%F yoo-etal-2025-dress
%X Automated essay scoring (AES) is a useful tool in English as a Foreign Language (EFL) writing education, offering real-time essay scores for students and instructors. However, previous AES models were trained on essays and scores irrelevant to the practical scenarios of EFL writing education and usually provided a single holistic score due to the lack of appropriate datasets. In this paper, we release DREsS, a large-scale, standard dataset for rubric-based automated essay scoring with 48.9K samples in total. DREsS comprises three sub-datasets: DREsS_New, DREsS_Std., and DREsS_CASE. We collect DREsS_New, a real-classroom dataset with 2.3K essays authored by EFL undergraduate students and scored by English education experts. We also standardize existing rubric-based essay scoring datasets as DREsS_Std. We suggest CASE, a corruption-based augmentation strategy for essays, which generates 40.1K synthetic samples of DREsS_CASE and improves the baseline results by 45.44%. DREsS will enable further research to provide a more accurate and practical AES system for EFL writing education.
%R 10.18653/v1/2025.acl-long.659
%U https://aclanthology.org/2025.acl-long.659/
%U https://doi.org/10.18653/v1/2025.acl-long.659
%P 13439-13454
Markdown (Informal)
[DREsS: Dataset for Rubric-based Essay Scoring on EFL Writing](https://aclanthology.org/2025.acl-long.659/) (Yoo et al., ACL 2025)
ACL
- Haneul Yoo, Jieun Han, So-Yeon Ahn, and Alice Oh. 2025. DREsS: Dataset for Rubric-based Essay Scoring on EFL Writing. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 13439–13454, Vienna, Austria. Association for Computational Linguistics.