@inproceedings{riordan-etal-2020-empirical,
title = "An empirical investigation of neural methods for content scoring of science explanations",
author = "Riordan, Brian and
Bichler, Sarah and
Bradford, Allison and
King Chen, Jennifer and
Wiley, Korah and
Gerard, Libby and
C. Linn, Marcia",
editor = "Burstein, Jill and
Kochmar, Ekaterina and
Leacock, Claudia and
Madnani, Nitin and
Pil{\'a}n, Ildik{\'o} and
Yannakoudakis, Helen and
Zesch, Torsten",
booktitle = "Proceedings of the Fifteenth Workshop on Innovative Use of NLP for Building Educational Applications",
month = jul,
year = "2020",
address = "Seattle, WA, USA {\textrightarrow} Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.bea-1.13/",
doi = "10.18653/v1/2020.bea-1.13",
pages = "135--144",
abstract = "With the widespread adoption of the Next Generation Science Standards (NGSS), science teachers and online learning environments face the challenge of evaluating students' integration of different dimensions of science learning. Recent advances in representation learning in natural language processing have proven effective across many natural language processing tasks, but a rigorous evaluation of the relative merits of these methods for scoring complex constructed response formative assessments has not previously been carried out. We present a detailed empirical investigation of feature-based, recurrent neural network, and pre-trained transformer models on scoring content in real-world formative assessment data. We demonstrate that recent neural methods can rival or exceed the performance of feature-based methods. We also provide evidence that different classes of neural models take advantage of different learning cues, and pre-trained transformer models may be more robust to spurious, dataset-specific learning cues, better reflecting scoring rubrics."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="riordan-etal-2020-empirical">
<titleInfo>
<title>An empirical investigation of neural methods for content scoring of science explanations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Brian</namePart>
<namePart type="family">Riordan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sarah</namePart>
<namePart type="family">Bichler</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Allison</namePart>
<namePart type="family">Bradford</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jennifer</namePart>
<namePart type="family">King Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Korah</namePart>
<namePart type="family">Wiley</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Libby</namePart>
<namePart type="family">Gerard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marcia</namePart>
<namePart type="family">C. Linn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifteenth Workshop on Innovative Use of NLP for Building Educational Applications</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jill</namePart>
<namePart type="family">Burstein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Kochmar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Claudia</namePart>
<namePart type="family">Leacock</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nitin</namePart>
<namePart type="family">Madnani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ildikó</namePart>
<namePart type="family">Pilán</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helen</namePart>
<namePart type="family">Yannakoudakis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Torsten</namePart>
<namePart type="family">Zesch</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Seattle, WA, USA → Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>With the widespread adoption of the Next Generation Science Standards (NGSS), science teachers and online learning environments face the challenge of evaluating students’ integration of different dimensions of science learning. Recent advances in representation learning in natural language processing have proven effective across many natural language processing tasks, but a rigorous evaluation of the relative merits of these methods for scoring complex constructed response formative assessments has not previously been carried out. We present a detailed empirical investigation of feature-based, recurrent neural network, and pre-trained transformer models on scoring content in real-world formative assessment data. We demonstrate that recent neural methods can rival or exceed the performance of feature-based methods. We also provide evidence that different classes of neural models take advantage of different learning cues, and pre-trained transformer models may be more robust to spurious, dataset-specific learning cues, better reflecting scoring rubrics.</abstract>
<identifier type="citekey">riordan-etal-2020-empirical</identifier>
<identifier type="doi">10.18653/v1/2020.bea-1.13</identifier>
<location>
<url>https://aclanthology.org/2020.bea-1.13/</url>
</location>
<part>
<date>2020-07</date>
<extent unit="page">
<start>135</start>
<end>144</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T An empirical investigation of neural methods for content scoring of science explanations
%A Riordan, Brian
%A Bichler, Sarah
%A Bradford, Allison
%A King Chen, Jennifer
%A Wiley, Korah
%A Gerard, Libby
%A C. Linn, Marcia
%Y Burstein, Jill
%Y Kochmar, Ekaterina
%Y Leacock, Claudia
%Y Madnani, Nitin
%Y Pilán, Ildikó
%Y Yannakoudakis, Helen
%Y Zesch, Torsten
%S Proceedings of the Fifteenth Workshop on Innovative Use of NLP for Building Educational Applications
%D 2020
%8 July
%I Association for Computational Linguistics
%C Seattle, WA, USA → Online
%F riordan-etal-2020-empirical
%X With the widespread adoption of the Next Generation Science Standards (NGSS), science teachers and online learning environments face the challenge of evaluating students’ integration of different dimensions of science learning. Recent advances in representation learning in natural language processing have proven effective across many natural language processing tasks, but a rigorous evaluation of the relative merits of these methods for scoring complex constructed response formative assessments has not previously been carried out. We present a detailed empirical investigation of feature-based, recurrent neural network, and pre-trained transformer models on scoring content in real-world formative assessment data. We demonstrate that recent neural methods can rival or exceed the performance of feature-based methods. We also provide evidence that different classes of neural models take advantage of different learning cues, and pre-trained transformer models may be more robust to spurious, dataset-specific learning cues, better reflecting scoring rubrics.
%R 10.18653/v1/2020.bea-1.13
%U https://aclanthology.org/2020.bea-1.13/
%U https://doi.org/10.18653/v1/2020.bea-1.13
%P 135-144
Markdown (Informal)
[An empirical investigation of neural methods for content scoring of science explanations](https://aclanthology.org/2020.bea-1.13/) (Riordan et al., BEA 2020)
ACL
- Brian Riordan, Sarah Bichler, Allison Bradford, Jennifer King Chen, Korah Wiley, Libby Gerard, and Marcia C. Linn. 2020. An empirical investigation of neural methods for content scoring of science explanations. In Proceedings of the Fifteenth Workshop on Innovative Use of NLP for Building Educational Applications, pages 135–144, Seattle, WA, USA → Online. Association for Computational Linguistics.