@inproceedings{sato-etal-2008-automatic,
title = "Automatic Assessment of {J}apanese Text Readability Based on a Textbook Corpus",
author = "Sato, Satoshi and
Matsuyoshi, Suguru and
Kondoh, Yohsuke",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Piperidis, Stelios and
Tapias, Daniel",
booktitle = "Proceedings of the Sixth International Conference on Language Resources and Evaluation ({LREC}'08)",
month = may,
year = "2008",
address = "Marrakech, Morocco",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2008/pdf/165_paper.pdf",
abstract = "This paper describes a method of readability measurement of Japanese texts based on a newly compiled textbook corpus. The textbook corpus consists of 1,478 sample passages extracted from 127 textbooks of elementary school, junior high school, high school, and university; it is divided into thirteen grade levels and the total size is about a million characters. For a given text passage, the readability measurement method determines the grade level to which the passage is the most similar by using character-unigram models, which are constructed from the textbook corpus. Because this method does not require sentence-boundary analysis and word-boundary analysis, it is applicable to texts that include incomplete sentences and non-regular text fragments. The performance of this method, which is measured by the correlation coefficient, is considerably high (R {\textgreater} 0.9); in case that the length of a text passage is limited in 25 characters, the correlation coefficient is still high (R = 0.83).",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sato-etal-2008-automatic">
<titleInfo>
<title>Automatic Assessment of Japanese Text Readability Based on a Textbook Corpus</title>
</titleInfo>
<name type="personal">
<namePart type="given">Satoshi</namePart>
<namePart type="family">Sato</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Suguru</namePart>
<namePart type="family">Matsuyoshi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yohsuke</namePart>
<namePart type="family">Kondoh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2008-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC’08)</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">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">Marrakech, Morocco</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper describes a method of readability measurement of Japanese texts based on a newly compiled textbook corpus. The textbook corpus consists of 1,478 sample passages extracted from 127 textbooks of elementary school, junior high school, high school, and university; it is divided into thirteen grade levels and the total size is about a million characters. For a given text passage, the readability measurement method determines the grade level to which the passage is the most similar by using character-unigram models, which are constructed from the textbook corpus. Because this method does not require sentence-boundary analysis and word-boundary analysis, it is applicable to texts that include incomplete sentences and non-regular text fragments. The performance of this method, which is measured by the correlation coefficient, is considerably high (R \textgreater 0.9); in case that the length of a text passage is limited in 25 characters, the correlation coefficient is still high (R = 0.83).</abstract>
<identifier type="citekey">sato-etal-2008-automatic</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2008/pdf/165_paper.pdf</url>
</location>
<part>
<date>2008-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Automatic Assessment of Japanese Text Readability Based on a Textbook Corpus
%A Sato, Satoshi
%A Matsuyoshi, Suguru
%A Kondoh, Yohsuke
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Piperidis, Stelios
%Y Tapias, Daniel
%S Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC’08)
%D 2008
%8 May
%I European Language Resources Association (ELRA)
%C Marrakech, Morocco
%F sato-etal-2008-automatic
%X This paper describes a method of readability measurement of Japanese texts based on a newly compiled textbook corpus. The textbook corpus consists of 1,478 sample passages extracted from 127 textbooks of elementary school, junior high school, high school, and university; it is divided into thirteen grade levels and the total size is about a million characters. For a given text passage, the readability measurement method determines the grade level to which the passage is the most similar by using character-unigram models, which are constructed from the textbook corpus. Because this method does not require sentence-boundary analysis and word-boundary analysis, it is applicable to texts that include incomplete sentences and non-regular text fragments. The performance of this method, which is measured by the correlation coefficient, is considerably high (R \textgreater 0.9); in case that the length of a text passage is limited in 25 characters, the correlation coefficient is still high (R = 0.83).
%U http://www.lrec-conf.org/proceedings/lrec2008/pdf/165_paper.pdf
Markdown (Informal)
[Automatic Assessment of Japanese Text Readability Based on a Textbook Corpus](http://www.lrec-conf.org/proceedings/lrec2008/pdf/165_paper.pdf) (Sato et al., LREC 2008)
ACL