@inproceedings{maekawa-etal-2010-design,
title = "Design, Compilation, and Preliminary Analyses of {B}alanced {C}orpus of {C}ontemporary {W}ritten {J}apanese",
author = "Maekawa, Kikuo and
Yamazaki, Makoto and
Maruyama, Takehiko and
Yamaguchi, Masaya and
Ogura, Hideki and
Kashino, Wakako and
Ogiso, Toshinobu and
Koiso, Hanae and
Den, Yasuharu",
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/99_Paper.pdf",
abstract = "Compilation of a 100 million words balanced corpus called the Balanced Corpus of Contemporary Written Japanese (or BCCWJ) is underway at the National Institute for Japanese Language and Linguistics. The corpus covers a wide range of text genres including books, magazines, newspapers, governmental white papers, textbooks, minutes of the National Diet, internet text (bulletin board and blogs) and so forth, and when possible, samples are drawn from the rigidly defined statistical populations by means of random sampling. All texts are dually POS-analyzed based upon two different, but mutually related, definitions of word. Currently, more than 90 million words have been sampled and XML annotated with respect to text-structure and lexical and character information. A preliminary linear discriminant analysis of text genres using the data of POS frequencies and sentence length revealed it was possible to classify the text genres with a correct identification rate of 88{\%} as far as the samples of books, newspapers, whitepapers, and internet bulletin boards are concerned. When the samples of blogs were included in this data set, however, the identification rate went down to 68{\%}, suggesting the considerable variance of the blog texts in terms of the textual register and style.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="maekawa-etal-2010-design">
<titleInfo>
<title>Design, Compilation, and Preliminary Analyses of Balanced Corpus of Contemporary Written Japanese</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kikuo</namePart>
<namePart type="family">Maekawa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Makoto</namePart>
<namePart type="family">Yamazaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Takehiko</namePart>
<namePart type="family">Maruyama</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Masaya</namePart>
<namePart type="family">Yamaguchi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hideki</namePart>
<namePart type="family">Ogura</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wakako</namePart>
<namePart type="family">Kashino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Toshinobu</namePart>
<namePart type="family">Ogiso</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hanae</namePart>
<namePart type="family">Koiso</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yasuharu</namePart>
<namePart type="family">Den</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>Compilation of a 100 million words balanced corpus called the Balanced Corpus of Contemporary Written Japanese (or BCCWJ) is underway at the National Institute for Japanese Language and Linguistics. The corpus covers a wide range of text genres including books, magazines, newspapers, governmental white papers, textbooks, minutes of the National Diet, internet text (bulletin board and blogs) and so forth, and when possible, samples are drawn from the rigidly defined statistical populations by means of random sampling. All texts are dually POS-analyzed based upon two different, but mutually related, definitions of word. Currently, more than 90 million words have been sampled and XML annotated with respect to text-structure and lexical and character information. A preliminary linear discriminant analysis of text genres using the data of POS frequencies and sentence length revealed it was possible to classify the text genres with a correct identification rate of 88% as far as the samples of books, newspapers, whitepapers, and internet bulletin boards are concerned. When the samples of blogs were included in this data set, however, the identification rate went down to 68%, suggesting the considerable variance of the blog texts in terms of the textual register and style.</abstract>
<identifier type="citekey">maekawa-etal-2010-design</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2010/pdf/99_Paper.pdf</url>
</location>
<part>
<date>2010-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Design, Compilation, and Preliminary Analyses of Balanced Corpus of Contemporary Written Japanese
%A Maekawa, Kikuo
%A Yamazaki, Makoto
%A Maruyama, Takehiko
%A Yamaguchi, Masaya
%A Ogura, Hideki
%A Kashino, Wakako
%A Ogiso, Toshinobu
%A Koiso, Hanae
%A Den, Yasuharu
%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 maekawa-etal-2010-design
%X Compilation of a 100 million words balanced corpus called the Balanced Corpus of Contemporary Written Japanese (or BCCWJ) is underway at the National Institute for Japanese Language and Linguistics. The corpus covers a wide range of text genres including books, magazines, newspapers, governmental white papers, textbooks, minutes of the National Diet, internet text (bulletin board and blogs) and so forth, and when possible, samples are drawn from the rigidly defined statistical populations by means of random sampling. All texts are dually POS-analyzed based upon two different, but mutually related, definitions of word. Currently, more than 90 million words have been sampled and XML annotated with respect to text-structure and lexical and character information. A preliminary linear discriminant analysis of text genres using the data of POS frequencies and sentence length revealed it was possible to classify the text genres with a correct identification rate of 88% as far as the samples of books, newspapers, whitepapers, and internet bulletin boards are concerned. When the samples of blogs were included in this data set, however, the identification rate went down to 68%, suggesting the considerable variance of the blog texts in terms of the textual register and style.
%U http://www.lrec-conf.org/proceedings/lrec2010/pdf/99_Paper.pdf
Markdown (Informal)
[Design, Compilation, and Preliminary Analyses of Balanced Corpus of Contemporary Written Japanese](http://www.lrec-conf.org/proceedings/lrec2010/pdf/99_Paper.pdf) (Maekawa et al., LREC 2010)
ACL
- Kikuo Maekawa, Makoto Yamazaki, Takehiko Maruyama, Masaya Yamaguchi, Hideki Ogura, Wakako Kashino, Toshinobu Ogiso, Hanae Koiso, and Yasuharu Den. 2010. Design, Compilation, and Preliminary Analyses of Balanced Corpus of Contemporary Written Japanese. In Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC'10), Valletta, Malta. European Language Resources Association (ELRA).