@inproceedings{shibata-uto-2022-analytic,
title = "Analytic Automated Essay Scoring Based on Deep Neural Networks Integrating Multidimensional Item Response Theory",
author = "Shibata, Takumi and
Uto, Masaki",
editor = "Calzolari, Nicoletta and
Huang, Chu-Ren and
Kim, Hansaem and
Pustejovsky, James and
Wanner, Leo and
Choi, Key-Sun and
Ryu, Pum-Mo and
Chen, Hsin-Hsi and
Donatelli, Lucia and
Ji, Heng and
Kurohashi, Sadao and
Paggio, Patrizia and
Xue, Nianwen and
Kim, Seokhwan and
Hahm, Younggyun and
He, Zhong and
Lee, Tony Kyungil and
Santus, Enrico and
Bond, Francis and
Na, Seung-Hoon",
booktitle = "Proceedings of the 29th International Conference on Computational Linguistics",
month = oct,
year = "2022",
address = "Gyeongju, Republic of Korea",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2022.coling-1.257",
pages = "2917--2926",
abstract = "Essay exams have been attracting attention as a way of measuring the higher-order abilities of examinees, but they have two major drawbacks in that grading them is expensive and raises questions about fairness. As an approach to overcome these problems, automated essay scoring (AES) is in increasing need. Many AES models based on deep neural networks have been proposed in recent years and have achieved high accuracy, but most of these models are designed to predict only a single overall score. However, to provide detailed feedback in practical situations, we often require not only the overall score but also analytic scores corresponding to various aspects of the essay. Several neural AES models that can predict both the analytic scores and the overall score have also been proposed for this very purpose. However, conventional models are designed to have complex neural architectures for each analytic score, which makes interpreting the score prediction difficult. To improve the interpretability of the prediction while maintaining scoring accuracy, we propose a new neural model for automated analytic scoring that integrates a multidimensional item response theory model, which is a popular psychometric model.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shibata-uto-2022-analytic">
<titleInfo>
<title>Analytic Automated Essay Scoring Based on Deep Neural Networks Integrating Multidimensional Item Response Theory</title>
</titleInfo>
<name type="personal">
<namePart type="given">Takumi</namePart>
<namePart type="family">Shibata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Masaki</namePart>
<namePart type="family">Uto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 29th International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chu-Ren</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hansaem</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">James</namePart>
<namePart type="family">Pustejovsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leo</namePart>
<namePart type="family">Wanner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Key-Sun</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pum-Mo</namePart>
<namePart type="family">Ryu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hsin-Hsi</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Donatelli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heng</namePart>
<namePart type="family">Ji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sadao</namePart>
<namePart type="family">Kurohashi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Patrizia</namePart>
<namePart type="family">Paggio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seokhwan</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Younggyun</namePart>
<namePart type="family">Hahm</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhong</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tony</namePart>
<namePart type="given">Kyungil</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Enrico</namePart>
<namePart type="family">Santus</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Francis</namePart>
<namePart type="family">Bond</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seung-Hoon</namePart>
<namePart type="family">Na</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Committee on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Gyeongju, Republic of Korea</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Essay exams have been attracting attention as a way of measuring the higher-order abilities of examinees, but they have two major drawbacks in that grading them is expensive and raises questions about fairness. As an approach to overcome these problems, automated essay scoring (AES) is in increasing need. Many AES models based on deep neural networks have been proposed in recent years and have achieved high accuracy, but most of these models are designed to predict only a single overall score. However, to provide detailed feedback in practical situations, we often require not only the overall score but also analytic scores corresponding to various aspects of the essay. Several neural AES models that can predict both the analytic scores and the overall score have also been proposed for this very purpose. However, conventional models are designed to have complex neural architectures for each analytic score, which makes interpreting the score prediction difficult. To improve the interpretability of the prediction while maintaining scoring accuracy, we propose a new neural model for automated analytic scoring that integrates a multidimensional item response theory model, which is a popular psychometric model.</abstract>
<identifier type="citekey">shibata-uto-2022-analytic</identifier>
<location>
<url>https://aclanthology.org/2022.coling-1.257</url>
</location>
<part>
<date>2022-10</date>
<extent unit="page">
<start>2917</start>
<end>2926</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Analytic Automated Essay Scoring Based on Deep Neural Networks Integrating Multidimensional Item Response Theory
%A Shibata, Takumi
%A Uto, Masaki
%Y Calzolari, Nicoletta
%Y Huang, Chu-Ren
%Y Kim, Hansaem
%Y Pustejovsky, James
%Y Wanner, Leo
%Y Choi, Key-Sun
%Y Ryu, Pum-Mo
%Y Chen, Hsin-Hsi
%Y Donatelli, Lucia
%Y Ji, Heng
%Y Kurohashi, Sadao
%Y Paggio, Patrizia
%Y Xue, Nianwen
%Y Kim, Seokhwan
%Y Hahm, Younggyun
%Y He, Zhong
%Y Lee, Tony Kyungil
%Y Santus, Enrico
%Y Bond, Francis
%Y Na, Seung-Hoon
%S Proceedings of the 29th International Conference on Computational Linguistics
%D 2022
%8 October
%I International Committee on Computational Linguistics
%C Gyeongju, Republic of Korea
%F shibata-uto-2022-analytic
%X Essay exams have been attracting attention as a way of measuring the higher-order abilities of examinees, but they have two major drawbacks in that grading them is expensive and raises questions about fairness. As an approach to overcome these problems, automated essay scoring (AES) is in increasing need. Many AES models based on deep neural networks have been proposed in recent years and have achieved high accuracy, but most of these models are designed to predict only a single overall score. However, to provide detailed feedback in practical situations, we often require not only the overall score but also analytic scores corresponding to various aspects of the essay. Several neural AES models that can predict both the analytic scores and the overall score have also been proposed for this very purpose. However, conventional models are designed to have complex neural architectures for each analytic score, which makes interpreting the score prediction difficult. To improve the interpretability of the prediction while maintaining scoring accuracy, we propose a new neural model for automated analytic scoring that integrates a multidimensional item response theory model, which is a popular psychometric model.
%U https://aclanthology.org/2022.coling-1.257
%P 2917-2926
Markdown (Informal)
[Analytic Automated Essay Scoring Based on Deep Neural Networks Integrating Multidimensional Item Response Theory](https://aclanthology.org/2022.coling-1.257) (Shibata & Uto, COLING 2022)
ACL