@inproceedings{horbach-etal-2014-finding,
title = "Finding a Tradeoff between Accuracy and Rater{'}s Workload in Grading Clustered Short Answers",
author = "Horbach, Andrea and
Palmer, Alexis and
Wolska, Magdalena",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Loftsson, Hrafn and
Maegaard, Bente and
Mariani, Joseph and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Ninth International Conference on Language Resources and Evaluation ({LREC}'14)",
month = may,
year = "2014",
address = "Reykjavik, Iceland",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2014/pdf/887_Paper.pdf",
pages = "588--595",
abstract = "n this paper we investigate the potential of answer clustering for semi-automatic scoring of short answer questions for German as a foreign language. We use surface features like word and character n-grams to cluster answers to listening comprehension exercises per question and simulate having human graders only label one answer per cluster and then propagating this label to all other members of the cluster. We investigate various ways to select this single item to be labeled and find that choosing the item closest to the centroid of a cluster leads to improved (simulated) grading accuracy over random item selection. Averaged over all questions, we can reduce a teachers workload to labeling only 40{\%} of all different answers for a question, while still maintaining a grading accuracy of more than 85{\%}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="horbach-etal-2014-finding">
<titleInfo>
<title>Finding a Tradeoff between Accuracy and Rater’s Workload in Grading Clustered Short Answers</title>
</titleInfo>
<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">Alexis</namePart>
<namePart type="family">Palmer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Magdalena</namePart>
<namePart type="family">Wolska</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2014-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)</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">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hrafn</namePart>
<namePart type="family">Loftsson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asuncion</namePart>
<namePart type="family">Moreno</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Reykjavik, Iceland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>n this paper we investigate the potential of answer clustering for semi-automatic scoring of short answer questions for German as a foreign language. We use surface features like word and character n-grams to cluster answers to listening comprehension exercises per question and simulate having human graders only label one answer per cluster and then propagating this label to all other members of the cluster. We investigate various ways to select this single item to be labeled and find that choosing the item closest to the centroid of a cluster leads to improved (simulated) grading accuracy over random item selection. Averaged over all questions, we can reduce a teachers workload to labeling only 40% of all different answers for a question, while still maintaining a grading accuracy of more than 85%.</abstract>
<identifier type="citekey">horbach-etal-2014-finding</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/887_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>588</start>
<end>595</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Finding a Tradeoff between Accuracy and Rater’s Workload in Grading Clustered Short Answers
%A Horbach, Andrea
%A Palmer, Alexis
%A Wolska, Magdalena
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Loftsson, Hrafn
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)
%D 2014
%8 May
%I European Language Resources Association (ELRA)
%C Reykjavik, Iceland
%F horbach-etal-2014-finding
%X n this paper we investigate the potential of answer clustering for semi-automatic scoring of short answer questions for German as a foreign language. We use surface features like word and character n-grams to cluster answers to listening comprehension exercises per question and simulate having human graders only label one answer per cluster and then propagating this label to all other members of the cluster. We investigate various ways to select this single item to be labeled and find that choosing the item closest to the centroid of a cluster leads to improved (simulated) grading accuracy over random item selection. Averaged over all questions, we can reduce a teachers workload to labeling only 40% of all different answers for a question, while still maintaining a grading accuracy of more than 85%.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/887_Paper.pdf
%P 588-595
Markdown (Informal)
[Finding a Tradeoff between Accuracy and Rater’s Workload in Grading Clustered Short Answers](http://www.lrec-conf.org/proceedings/lrec2014/pdf/887_Paper.pdf) (Horbach et al., LREC 2014)
ACL