@inproceedings{gunduz-etal-2025-enhancing,
title = "Enhancing Essay Scoring with {GPT}-2 Using Back Translation Techniques",
author = "Gunduz, Aysegul and
Gierl, Mark and
Bulut, Okan",
editor = "Wilson, Joshua and
Ormerod, Christopher and
Beiting Parrish, Magdalen",
booktitle = "Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Full Papers",
month = oct,
year = "2025",
address = "Wyndham Grand Pittsburgh, Downtown, Pittsburgh, Pennsylvania, United States",
publisher = "National Council on Measurement in Education (NCME)",
url = "https://aclanthology.org/2025.aimecon-main.44/",
pages = "406--416",
ISBN = "979-8-218-84228-4",
abstract = "This study evaluates GPT-2 (small) for automated essay scoring on the ASAP dataset. Back-translation (English{--}Turkish{--}English) improved performance, especially on imbalanced sets. QWK scores peaked at 0.77. Findings highlight augmentation{'}s value and the need for more advanced, rubric-aware models for fairer assessment."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gunduz-etal-2025-enhancing">
<titleInfo>
<title>Enhancing Essay Scoring with GPT-2 Using Back Translation Techniques</title>
</titleInfo>
<name type="personal">
<namePart type="given">Aysegul</namePart>
<namePart type="family">Gunduz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mark</namePart>
<namePart type="family">Gierl</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Okan</namePart>
<namePart type="family">Bulut</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Full Papers</title>
</titleInfo>
<name type="personal">
<namePart type="given">Joshua</namePart>
<namePart type="family">Wilson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Ormerod</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Magdalen</namePart>
<namePart type="family">Beiting Parrish</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>National Council on Measurement in Education (NCME)</publisher>
<place>
<placeTerm type="text">Wyndham Grand Pittsburgh, Downtown, Pittsburgh, Pennsylvania, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-218-84228-4</identifier>
</relatedItem>
<abstract>This study evaluates GPT-2 (small) for automated essay scoring on the ASAP dataset. Back-translation (English–Turkish–English) improved performance, especially on imbalanced sets. QWK scores peaked at 0.77. Findings highlight augmentation’s value and the need for more advanced, rubric-aware models for fairer assessment.</abstract>
<identifier type="citekey">gunduz-etal-2025-enhancing</identifier>
<location>
<url>https://aclanthology.org/2025.aimecon-main.44/</url>
</location>
<part>
<date>2025-10</date>
<extent unit="page">
<start>406</start>
<end>416</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Enhancing Essay Scoring with GPT-2 Using Back Translation Techniques
%A Gunduz, Aysegul
%A Gierl, Mark
%A Bulut, Okan
%Y Wilson, Joshua
%Y Ormerod, Christopher
%Y Beiting Parrish, Magdalen
%S Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Full Papers
%D 2025
%8 October
%I National Council on Measurement in Education (NCME)
%C Wyndham Grand Pittsburgh, Downtown, Pittsburgh, Pennsylvania, United States
%@ 979-8-218-84228-4
%F gunduz-etal-2025-enhancing
%X This study evaluates GPT-2 (small) for automated essay scoring on the ASAP dataset. Back-translation (English–Turkish–English) improved performance, especially on imbalanced sets. QWK scores peaked at 0.77. Findings highlight augmentation’s value and the need for more advanced, rubric-aware models for fairer assessment.
%U https://aclanthology.org/2025.aimecon-main.44/
%P 406-416
Markdown (Informal)
[Enhancing Essay Scoring with GPT-2 Using Back Translation Techniques](https://aclanthology.org/2025.aimecon-main.44/) (Gunduz et al., AIME-Con 2025)
ACL
- Aysegul Gunduz, Mark Gierl, and Okan Bulut. 2025. Enhancing Essay Scoring with GPT-2 Using Back Translation Techniques. In Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Full Papers, pages 406–416, Wyndham Grand Pittsburgh, Downtown, Pittsburgh, Pennsylvania, United States. National Council on Measurement in Education (NCME).