@inproceedings{bexte-etal-2023-similarity,
title = "Similarity-Based Content Scoring - A more Classroom-Suitable Alternative to Instance-Based Scoring?",
author = "Bexte, Marie and
Horbach, Andrea and
Zesch, Torsten",
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.119",
doi = "10.18653/v1/2023.findings-acl.119",
pages = "1892--1903",
abstract = "Automatically scoring student answers is an important task that is usually solved using instance-based supervised learning. Recently, similarity-based scoring has been proposed as an alternative approach yielding similar perfor- mance. It has hypothetical advantages such as a lower need for annotated training data and better zero-shot performance, both of which are properties that would be highly beneficial when applying content scoring in a realistic classroom setting. In this paper we take a closer look at these alleged advantages by comparing different instance-based and similarity-based methods on multiple data sets in a number of learning curve experiments. We find that both the demand on data and cross-prompt performance is similar, thus not confirming the former two suggested advantages. The by default more straightforward possibility to give feedback based on a similarity-based approach may thus tip the scales in favor of it, although future work is needed to explore this advantage in practice.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bexte-etal-2023-similarity">
<titleInfo>
<title>Similarity-Based Content Scoring - A more Classroom-Suitable Alternative to Instance-Based Scoring?</title>
</titleInfo>
<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>
<name type="personal">
<namePart type="given">Torsten</namePart>
<namePart type="family">Zesch</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>Automatically scoring student answers is an important task that is usually solved using instance-based supervised learning. Recently, similarity-based scoring has been proposed as an alternative approach yielding similar perfor- mance. It has hypothetical advantages such as a lower need for annotated training data and better zero-shot performance, both of which are properties that would be highly beneficial when applying content scoring in a realistic classroom setting. In this paper we take a closer look at these alleged advantages by comparing different instance-based and similarity-based methods on multiple data sets in a number of learning curve experiments. We find that both the demand on data and cross-prompt performance is similar, thus not confirming the former two suggested advantages. The by default more straightforward possibility to give feedback based on a similarity-based approach may thus tip the scales in favor of it, although future work is needed to explore this advantage in practice.</abstract>
<identifier type="citekey">bexte-etal-2023-similarity</identifier>
<identifier type="doi">10.18653/v1/2023.findings-acl.119</identifier>
<location>
<url>https://aclanthology.org/2023.findings-acl.119</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>1892</start>
<end>1903</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Similarity-Based Content Scoring - A more Classroom-Suitable Alternative to Instance-Based Scoring?
%A Bexte, Marie
%A Horbach, Andrea
%A Zesch, Torsten
%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 bexte-etal-2023-similarity
%X Automatically scoring student answers is an important task that is usually solved using instance-based supervised learning. Recently, similarity-based scoring has been proposed as an alternative approach yielding similar perfor- mance. It has hypothetical advantages such as a lower need for annotated training data and better zero-shot performance, both of which are properties that would be highly beneficial when applying content scoring in a realistic classroom setting. In this paper we take a closer look at these alleged advantages by comparing different instance-based and similarity-based methods on multiple data sets in a number of learning curve experiments. We find that both the demand on data and cross-prompt performance is similar, thus not confirming the former two suggested advantages. The by default more straightforward possibility to give feedback based on a similarity-based approach may thus tip the scales in favor of it, although future work is needed to explore this advantage in practice.
%R 10.18653/v1/2023.findings-acl.119
%U https://aclanthology.org/2023.findings-acl.119
%U https://doi.org/10.18653/v1/2023.findings-acl.119
%P 1892-1903
Markdown (Informal)
[Similarity-Based Content Scoring - A more Classroom-Suitable Alternative to Instance-Based Scoring?](https://aclanthology.org/2023.findings-acl.119) (Bexte et al., Findings 2023)
ACL