@inproceedings{ding-etal-2023-score,
title = "Score It All Together: A Multi-Task Learning Study on Automatic Scoring of Argumentative Essays",
author = "Ding, Yuning and
Bexte, Marie and
Horbach, Andrea",
editor = "Rogers, Anna and
Boyd-Graber, Jordan and
Okazaki, Naoaki",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2023",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-acl.825",
doi = "10.18653/v1/2023.findings-acl.825",
pages = "13052--13063",
abstract = "When scoring argumentative essays in an educational context, not only the presence or absence of certain argumentative elements but also their quality is important. On the recently published student essay dataset PERSUADE, we first show that the automatic scoring of argument quality benefits from additional information about context, writing prompt and argument type. We then explore the different combinations of three tasks: automated span detection, type and quality prediction. Results show that a multi-task learning approach combining the three tasks outperforms sequential approaches that first learn to segment and then predict the quality/type of a segment.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ding-etal-2023-score">
<titleInfo>
<title>Score It All Together: A Multi-Task Learning Study on Automatic Scoring of Argumentative Essays</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yuning</namePart>
<namePart type="family">Ding</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marie</namePart>
<namePart type="family">Bexte</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrea</namePart>
<namePart type="family">Horbach</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rogers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jordan</namePart>
<namePart type="family">Boyd-Graber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naoaki</namePart>
<namePart type="family">Okazaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>When scoring argumentative essays in an educational context, not only the presence or absence of certain argumentative elements but also their quality is important. On the recently published student essay dataset PERSUADE, we first show that the automatic scoring of argument quality benefits from additional information about context, writing prompt and argument type. We then explore the different combinations of three tasks: automated span detection, type and quality prediction. Results show that a multi-task learning approach combining the three tasks outperforms sequential approaches that first learn to segment and then predict the quality/type of a segment.</abstract>
<identifier type="citekey">ding-etal-2023-score</identifier>
<identifier type="doi">10.18653/v1/2023.findings-acl.825</identifier>
<location>
<url>https://aclanthology.org/2023.findings-acl.825</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>13052</start>
<end>13063</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Score It All Together: A Multi-Task Learning Study on Automatic Scoring of Argumentative Essays
%A Ding, Yuning
%A Bexte, Marie
%A Horbach, Andrea
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Findings of the Association for Computational Linguistics: ACL 2023
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F ding-etal-2023-score
%X When scoring argumentative essays in an educational context, not only the presence or absence of certain argumentative elements but also their quality is important. On the recently published student essay dataset PERSUADE, we first show that the automatic scoring of argument quality benefits from additional information about context, writing prompt and argument type. We then explore the different combinations of three tasks: automated span detection, type and quality prediction. Results show that a multi-task learning approach combining the three tasks outperforms sequential approaches that first learn to segment and then predict the quality/type of a segment.
%R 10.18653/v1/2023.findings-acl.825
%U https://aclanthology.org/2023.findings-acl.825
%U https://doi.org/10.18653/v1/2023.findings-acl.825
%P 13052-13063
Markdown (Informal)
[Score It All Together: A Multi-Task Learning Study on Automatic Scoring of Argumentative Essays](https://aclanthology.org/2023.findings-acl.825) (Ding et al., Findings 2023)
ACL