@inproceedings{panunzi-etal-2012-ridire,
title = "{RIDIRE}-{CPI}: an Open Source Crawling and Processing Infrastructure for Supervised Web-Corpora Building",
author = "Panunzi, Alessandro and
Fabbri, Marco and
Moneglia, Massimo and
Gregori, Lorenzo and
Paladini, Samuele",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Do{\u{g}}an, Mehmet U{\u{g}}ur and
Maegaard, Bente and
Mariani, Joseph and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Eighth International Conference on Language Resources and Evaluation ({LREC}`12)",
month = may,
year = "2012",
address = "Istanbul, Turkey",
publisher = "European Language Resources Association (ELRA)",
url = "https://aclanthology.org/L12-1309/",
pages = "2274--2279",
abstract = "This paper introduces the RIDIRE-CPI, an open source tool for the building of web corpora with a specific design through a targeted crawling strategy. The tool has been developed within the RIDIRE Project, which aims at creating a 2 billion word balanced web corpus for Italian. RIDIRE-CPI architecture integrates existing open source tools as well as modules developed specifically within the RIDIRE project. It consists of various components: a robust crawler (Heritrix), a user friendly web interface, several conversion and cleaning tools, an anti-duplicate filter, a language guesser, and a PoS tagger. The RIDIRE-CPI user-friendly interface is specifically intended for allowing collaborative work performance by users with low skills in web technology and text processing. Moreover, RIDIRE-CPI integrates a validation interface dedicated to the evaluation of the targeted crawling. Through the content selection, metadata assignment, and validation procedures, the RIDIRE-CPI allows the gathering of linguistic data with a supervised strategy that leads to a higher level of control of the corpus contents. The modular architecture of the infrastructure and its open-source distribution will assure the reusability of the tool for other corpus building initiatives."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="panunzi-etal-2012-ridire">
<titleInfo>
<title>RIDIRE-CPI: an Open Source Crawling and Processing Infrastructure for Supervised Web-Corpora Building</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Panunzi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marco</namePart>
<namePart type="family">Fabbri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Massimo</namePart>
<namePart type="family">Moneglia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lorenzo</namePart>
<namePart type="family">Gregori</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Samuele</namePart>
<namePart type="family">Paladini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2012-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC‘12)</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">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mehmet</namePart>
<namePart type="given">Uğur</namePart>
<namePart type="family">Doğan</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">Asuncion</namePart>
<namePart type="family">Moreno</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>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Istanbul, Turkey</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper introduces the RIDIRE-CPI, an open source tool for the building of web corpora with a specific design through a targeted crawling strategy. The tool has been developed within the RIDIRE Project, which aims at creating a 2 billion word balanced web corpus for Italian. RIDIRE-CPI architecture integrates existing open source tools as well as modules developed specifically within the RIDIRE project. It consists of various components: a robust crawler (Heritrix), a user friendly web interface, several conversion and cleaning tools, an anti-duplicate filter, a language guesser, and a PoS tagger. The RIDIRE-CPI user-friendly interface is specifically intended for allowing collaborative work performance by users with low skills in web technology and text processing. Moreover, RIDIRE-CPI integrates a validation interface dedicated to the evaluation of the targeted crawling. Through the content selection, metadata assignment, and validation procedures, the RIDIRE-CPI allows the gathering of linguistic data with a supervised strategy that leads to a higher level of control of the corpus contents. The modular architecture of the infrastructure and its open-source distribution will assure the reusability of the tool for other corpus building initiatives.</abstract>
<identifier type="citekey">panunzi-etal-2012-ridire</identifier>
<location>
<url>https://aclanthology.org/L12-1309/</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>2274</start>
<end>2279</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T RIDIRE-CPI: an Open Source Crawling and Processing Infrastructure for Supervised Web-Corpora Building
%A Panunzi, Alessandro
%A Fabbri, Marco
%A Moneglia, Massimo
%A Gregori, Lorenzo
%A Paladini, Samuele
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Doğan, Mehmet Uğur
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC‘12)
%D 2012
%8 May
%I European Language Resources Association (ELRA)
%C Istanbul, Turkey
%F panunzi-etal-2012-ridire
%X This paper introduces the RIDIRE-CPI, an open source tool for the building of web corpora with a specific design through a targeted crawling strategy. The tool has been developed within the RIDIRE Project, which aims at creating a 2 billion word balanced web corpus for Italian. RIDIRE-CPI architecture integrates existing open source tools as well as modules developed specifically within the RIDIRE project. It consists of various components: a robust crawler (Heritrix), a user friendly web interface, several conversion and cleaning tools, an anti-duplicate filter, a language guesser, and a PoS tagger. The RIDIRE-CPI user-friendly interface is specifically intended for allowing collaborative work performance by users with low skills in web technology and text processing. Moreover, RIDIRE-CPI integrates a validation interface dedicated to the evaluation of the targeted crawling. Through the content selection, metadata assignment, and validation procedures, the RIDIRE-CPI allows the gathering of linguistic data with a supervised strategy that leads to a higher level of control of the corpus contents. The modular architecture of the infrastructure and its open-source distribution will assure the reusability of the tool for other corpus building initiatives.
%U https://aclanthology.org/L12-1309/
%P 2274-2279
Markdown (Informal)
[RIDIRE-CPI: an Open Source Crawling and Processing Infrastructure for Supervised Web-Corpora Building](https://aclanthology.org/L12-1309/) (Panunzi et al., LREC 2012)
ACL