@inproceedings{shinzato-etal-2008-large,
title = "A Large-Scale Web Data Collection as a Natural Language Processing Infrastructure",
author = "Shinzato, Keiji and
Kawahara, Daisuke and
Hashimoto, Chikara and
Kurohashi, Sadao",
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/564_paper.pdf",
abstract = "In recent years, language resources acquired from theWeb are released, and these data improve the performance of applications in several NLP tasks. Although the language resources based on the web page unit are useful in NLP tasks and applications such as knowledge acquisition, document retrieval and document summarization, such language resources are not released so far. In this paper, we propose a data format for results of web page processing, and a search engine infrastructure which makes it possible to share approximately 100 million Japanese web data. By obtaining the web data, NLP researchers are enabled to begin their own processing immediately without analyzing web pages by themselves.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shinzato-etal-2008-large">
<titleInfo>
<title>A Large-Scale Web Data Collection as a Natural Language Processing Infrastructure</title>
</titleInfo>
<name type="personal">
<namePart type="given">Keiji</namePart>
<namePart type="family">Shinzato</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daisuke</namePart>
<namePart type="family">Kawahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chikara</namePart>
<namePart type="family">Hashimoto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sadao</namePart>
<namePart type="family">Kurohashi</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>In recent years, language resources acquired from theWeb are released, and these data improve the performance of applications in several NLP tasks. Although the language resources based on the web page unit are useful in NLP tasks and applications such as knowledge acquisition, document retrieval and document summarization, such language resources are not released so far. In this paper, we propose a data format for results of web page processing, and a search engine infrastructure which makes it possible to share approximately 100 million Japanese web data. By obtaining the web data, NLP researchers are enabled to begin their own processing immediately without analyzing web pages by themselves.</abstract>
<identifier type="citekey">shinzato-etal-2008-large</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2008/pdf/564_paper.pdf</url>
</location>
<part>
<date>2008-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Large-Scale Web Data Collection as a Natural Language Processing Infrastructure
%A Shinzato, Keiji
%A Kawahara, Daisuke
%A Hashimoto, Chikara
%A Kurohashi, Sadao
%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 shinzato-etal-2008-large
%X In recent years, language resources acquired from theWeb are released, and these data improve the performance of applications in several NLP tasks. Although the language resources based on the web page unit are useful in NLP tasks and applications such as knowledge acquisition, document retrieval and document summarization, such language resources are not released so far. In this paper, we propose a data format for results of web page processing, and a search engine infrastructure which makes it possible to share approximately 100 million Japanese web data. By obtaining the web data, NLP researchers are enabled to begin their own processing immediately without analyzing web pages by themselves.
%U http://www.lrec-conf.org/proceedings/lrec2008/pdf/564_paper.pdf
Markdown (Informal)
[A Large-Scale Web Data Collection as a Natural Language Processing Infrastructure](http://www.lrec-conf.org/proceedings/lrec2008/pdf/564_paper.pdf) (Shinzato et al., LREC 2008)
ACL