@inproceedings{van-oosten-etal-2010-towards,
title = "Towards an Improved Methodology for Automated Readability Prediction",
author = "van Oosten, Philip and
Tanghe, Dries and
Hoste, V{\'e}ronique",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Piperidis, Stelios and
Rosner, Mike and
Tapias, Daniel",
booktitle = "Proceedings of the Seventh International Conference on Language Resources and Evaluation ({LREC}'10)",
month = may,
year = "2010",
address = "Valletta, Malta",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2010/pdf/286_Paper.pdf",
abstract = "Since the first half of the 20th century, readability formulas have been widely employed to automatically predict the readability of an unseen text. In this article, the formulas and the text characteristics they are composed of are evaluated in the context of large Dutch and English corpora. We describe the behaviour of the formulas and the text characteristics by means of correlation matrices and a principal component analysis, and test the methodological validity of the formulas by means of collinearity tests. Both the correlation matrices and the principal component analysis show that the formulas described in this paper strongly correspond, regardless of the language for which they were designed. Furthermore, the collinearity test reveals shortcomings in the methodology that was used to create some of the existing readability formulas. All of this leads us to conclude that a new readability prediction method is needed. We finally make suggestions to come to a cleaner methodology and present web applications that will help us collect data to compile a new gold standard for readability prediction.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="van-oosten-etal-2010-towards">
<titleInfo>
<title>Towards an Improved Methodology for Automated Readability Prediction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Philip</namePart>
<namePart type="family">van Oosten</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dries</namePart>
<namePart type="family">Tanghe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Véronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2010-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC’10)</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">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">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>
<name type="personal">
<namePart type="given">Mike</namePart>
<namePart type="family">Rosner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Tapias</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Valletta, Malta</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Since the first half of the 20th century, readability formulas have been widely employed to automatically predict the readability of an unseen text. In this article, the formulas and the text characteristics they are composed of are evaluated in the context of large Dutch and English corpora. We describe the behaviour of the formulas and the text characteristics by means of correlation matrices and a principal component analysis, and test the methodological validity of the formulas by means of collinearity tests. Both the correlation matrices and the principal component analysis show that the formulas described in this paper strongly correspond, regardless of the language for which they were designed. Furthermore, the collinearity test reveals shortcomings in the methodology that was used to create some of the existing readability formulas. All of this leads us to conclude that a new readability prediction method is needed. We finally make suggestions to come to a cleaner methodology and present web applications that will help us collect data to compile a new gold standard for readability prediction.</abstract>
<identifier type="citekey">van-oosten-etal-2010-towards</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2010/pdf/286_Paper.pdf</url>
</location>
<part>
<date>2010-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Towards an Improved Methodology for Automated Readability Prediction
%A van Oosten, Philip
%A Tanghe, Dries
%A Hoste, Véronique
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Piperidis, Stelios
%Y Rosner, Mike
%Y Tapias, Daniel
%S Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC’10)
%D 2010
%8 May
%I European Language Resources Association (ELRA)
%C Valletta, Malta
%F van-oosten-etal-2010-towards
%X Since the first half of the 20th century, readability formulas have been widely employed to automatically predict the readability of an unseen text. In this article, the formulas and the text characteristics they are composed of are evaluated in the context of large Dutch and English corpora. We describe the behaviour of the formulas and the text characteristics by means of correlation matrices and a principal component analysis, and test the methodological validity of the formulas by means of collinearity tests. Both the correlation matrices and the principal component analysis show that the formulas described in this paper strongly correspond, regardless of the language for which they were designed. Furthermore, the collinearity test reveals shortcomings in the methodology that was used to create some of the existing readability formulas. All of this leads us to conclude that a new readability prediction method is needed. We finally make suggestions to come to a cleaner methodology and present web applications that will help us collect data to compile a new gold standard for readability prediction.
%U http://www.lrec-conf.org/proceedings/lrec2010/pdf/286_Paper.pdf
Markdown (Informal)
[Towards an Improved Methodology for Automated Readability Prediction](http://www.lrec-conf.org/proceedings/lrec2010/pdf/286_Paper.pdf) (van Oosten et al., LREC 2010)
ACL