@inproceedings{jeon-strube-2021-countering,
title = "Countering the Influence of Essay Length in Neural Essay Scoring",
author = "Jeon, Sungho and
Strube, Michael",
editor = "Moosavi, Nafise Sadat and
Gurevych, Iryna and
Fan, Angela and
Wolf, Thomas and
Hou, Yufang and
Marasovi{\'c}, Ana and
Ravi, Sujith",
booktitle = "Proceedings of the Second Workshop on Simple and Efficient Natural Language Processing",
month = nov,
year = "2021",
address = "Virtual",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.sustainlp-1.4/",
doi = "10.18653/v1/2021.sustainlp-1.4",
pages = "32--38",
abstract = "Previous work has shown that automated essay scoring systems, in particular machine learning-based systems, are not capable of assessing the quality of essays, but are relying on essay length, a factor irrelevant to writing proficiency. In this work, we first show that state-of-the-art systems, recent neural essay scoring systems, might be also influenced by the correlation between essay length and scores in a standard dataset. In our evaluation, a very simple neural model shows the state-of-the-art performance on the standard dataset. To consider essay content without taking essay length into account, we introduce a simple neural model assessing the similarity of content between an input essay and essays assigned different scores. This neural model achieves performance comparable to the state of the art on a standard dataset as well as on a second dataset. Our findings suggest that neural essay scoring systems should consider the characteristics of datasets to focus on text quality."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jeon-strube-2021-countering">
<titleInfo>
<title>Countering the Influence of Essay Length in Neural Essay Scoring</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sungho</namePart>
<namePart type="family">Jeon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Strube</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Second Workshop on Simple and Efficient Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nafise</namePart>
<namePart type="given">Sadat</namePart>
<namePart type="family">Moosavi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Iryna</namePart>
<namePart type="family">Gurevych</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Angela</namePart>
<namePart type="family">Fan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thomas</namePart>
<namePart type="family">Wolf</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yufang</namePart>
<namePart type="family">Hou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ana</namePart>
<namePart type="family">Marasović</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sujith</namePart>
<namePart type="family">Ravi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Virtual</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Previous work has shown that automated essay scoring systems, in particular machine learning-based systems, are not capable of assessing the quality of essays, but are relying on essay length, a factor irrelevant to writing proficiency. In this work, we first show that state-of-the-art systems, recent neural essay scoring systems, might be also influenced by the correlation between essay length and scores in a standard dataset. In our evaluation, a very simple neural model shows the state-of-the-art performance on the standard dataset. To consider essay content without taking essay length into account, we introduce a simple neural model assessing the similarity of content between an input essay and essays assigned different scores. This neural model achieves performance comparable to the state of the art on a standard dataset as well as on a second dataset. Our findings suggest that neural essay scoring systems should consider the characteristics of datasets to focus on text quality.</abstract>
<identifier type="citekey">jeon-strube-2021-countering</identifier>
<identifier type="doi">10.18653/v1/2021.sustainlp-1.4</identifier>
<location>
<url>https://aclanthology.org/2021.sustainlp-1.4/</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>32</start>
<end>38</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Countering the Influence of Essay Length in Neural Essay Scoring
%A Jeon, Sungho
%A Strube, Michael
%Y Moosavi, Nafise Sadat
%Y Gurevych, Iryna
%Y Fan, Angela
%Y Wolf, Thomas
%Y Hou, Yufang
%Y Marasović, Ana
%Y Ravi, Sujith
%S Proceedings of the Second Workshop on Simple and Efficient Natural Language Processing
%D 2021
%8 November
%I Association for Computational Linguistics
%C Virtual
%F jeon-strube-2021-countering
%X Previous work has shown that automated essay scoring systems, in particular machine learning-based systems, are not capable of assessing the quality of essays, but are relying on essay length, a factor irrelevant to writing proficiency. In this work, we first show that state-of-the-art systems, recent neural essay scoring systems, might be also influenced by the correlation between essay length and scores in a standard dataset. In our evaluation, a very simple neural model shows the state-of-the-art performance on the standard dataset. To consider essay content without taking essay length into account, we introduce a simple neural model assessing the similarity of content between an input essay and essays assigned different scores. This neural model achieves performance comparable to the state of the art on a standard dataset as well as on a second dataset. Our findings suggest that neural essay scoring systems should consider the characteristics of datasets to focus on text quality.
%R 10.18653/v1/2021.sustainlp-1.4
%U https://aclanthology.org/2021.sustainlp-1.4/
%U https://doi.org/10.18653/v1/2021.sustainlp-1.4
%P 32-38
Markdown (Informal)
[Countering the Influence of Essay Length in Neural Essay Scoring](https://aclanthology.org/2021.sustainlp-1.4/) (Jeon & Strube, sustainlp 2021)
ACL