@inproceedings{baroni-etal-2008-cleaneval,
title = "{C}leaneval: a Competition for Cleaning Web Pages",
author = "Baroni, Marco and
Chantree, Francis and
Kilgarriff, Adam and
Sharoff, Serge",
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/162_paper.pdf",
abstract = "Cleaneval is a shared task and competitive evaluation on the topic of cleaning arbitrary web pages, with the goal of preparing web data for use as a corpus for linguistic and language technology research and development. The first exercise took place in 2007. We describe how it was set up, results, and lessons learnt",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="baroni-etal-2008-cleaneval">
<titleInfo>
<title>Cleaneval: a Competition for Cleaning Web Pages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marco</namePart>
<namePart type="family">Baroni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Francis</namePart>
<namePart type="family">Chantree</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Adam</namePart>
<namePart type="family">Kilgarriff</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Serge</namePart>
<namePart type="family">Sharoff</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>Cleaneval is a shared task and competitive evaluation on the topic of cleaning arbitrary web pages, with the goal of preparing web data for use as a corpus for linguistic and language technology research and development. The first exercise took place in 2007. We describe how it was set up, results, and lessons learnt</abstract>
<identifier type="citekey">baroni-etal-2008-cleaneval</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2008/pdf/162_paper.pdf</url>
</location>
<part>
<date>2008-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Cleaneval: a Competition for Cleaning Web Pages
%A Baroni, Marco
%A Chantree, Francis
%A Kilgarriff, Adam
%A Sharoff, Serge
%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 baroni-etal-2008-cleaneval
%X Cleaneval is a shared task and competitive evaluation on the topic of cleaning arbitrary web pages, with the goal of preparing web data for use as a corpus for linguistic and language technology research and development. The first exercise took place in 2007. We describe how it was set up, results, and lessons learnt
%U http://www.lrec-conf.org/proceedings/lrec2008/pdf/162_paper.pdf
Markdown (Informal)
[Cleaneval: a Competition for Cleaning Web Pages](http://www.lrec-conf.org/proceedings/lrec2008/pdf/162_paper.pdf) (Baroni et al., LREC 2008)
ACL
- Marco Baroni, Francis Chantree, Adam Kilgarriff, and Serge Sharoff. 2008. Cleaneval: a Competition for Cleaning Web Pages. In Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC'08), Marrakech, Morocco. European Language Resources Association (ELRA).