@inproceedings{medelyan-etal-2006-language,
title = "Language Specific and Topic Focused Web Crawling",
author = "Medelyan, Olena and
Schulz, Stefan and
Paetzold, Jan and
Poprat, Michael and
Mark{\'o}, Korn{\'e}l",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Gangemi, Aldo and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Tapias, Daniel",
booktitle = "Proceedings of the Fifth International Conference on Language Resources and Evaluation ({LREC}{'}06)",
month = may,
year = "2006",
address = "Genoa, Italy",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2006/pdf/228_pdf.pdf",
abstract = "We describe an experiment on collecting large language and topic specific corpora automatically by using a focused Web crawler. Our crawler combines efficient crawling techniques with a common text classification tool. Given a sample corpus of medical documents, we automatically extract query phrases and then acquire seed URLs with a standard search engine. Starting from these seed URLs, the crawler builds a new large collection consisting only of documents that satisfy both the language and the topic model. The manual analysis of acquired English and German medicine corpora reveals the high accuracy of the crawler. However, there are significant differences between both languages.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="medelyan-etal-2006-language">
<titleInfo>
<title>Language Specific and Topic Focused Web Crawling</title>
</titleInfo>
<name type="personal">
<namePart type="given">Olena</namePart>
<namePart type="family">Medelyan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stefan</namePart>
<namePart type="family">Schulz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Paetzold</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Poprat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kornél</namePart>
<namePart type="family">Markó</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2006-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifth International Conference on Language Resources and Evaluation (LREC’06)</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">Aldo</namePart>
<namePart type="family">Gangemi</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">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">Genoa, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We describe an experiment on collecting large language and topic specific corpora automatically by using a focused Web crawler. Our crawler combines efficient crawling techniques with a common text classification tool. Given a sample corpus of medical documents, we automatically extract query phrases and then acquire seed URLs with a standard search engine. Starting from these seed URLs, the crawler builds a new large collection consisting only of documents that satisfy both the language and the topic model. The manual analysis of acquired English and German medicine corpora reveals the high accuracy of the crawler. However, there are significant differences between both languages.</abstract>
<identifier type="citekey">medelyan-etal-2006-language</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2006/pdf/228_pdf.pdf</url>
</location>
<part>
<date>2006-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Language Specific and Topic Focused Web Crawling
%A Medelyan, Olena
%A Schulz, Stefan
%A Paetzold, Jan
%A Poprat, Michael
%A Markó, Kornél
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Gangemi, Aldo
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Tapias, Daniel
%S Proceedings of the Fifth International Conference on Language Resources and Evaluation (LREC’06)
%D 2006
%8 May
%I European Language Resources Association (ELRA)
%C Genoa, Italy
%F medelyan-etal-2006-language
%X We describe an experiment on collecting large language and topic specific corpora automatically by using a focused Web crawler. Our crawler combines efficient crawling techniques with a common text classification tool. Given a sample corpus of medical documents, we automatically extract query phrases and then acquire seed URLs with a standard search engine. Starting from these seed URLs, the crawler builds a new large collection consisting only of documents that satisfy both the language and the topic model. The manual analysis of acquired English and German medicine corpora reveals the high accuracy of the crawler. However, there are significant differences between both languages.
%U http://www.lrec-conf.org/proceedings/lrec2006/pdf/228_pdf.pdf
Markdown (Informal)
[Language Specific and Topic Focused Web Crawling](http://www.lrec-conf.org/proceedings/lrec2006/pdf/228_pdf.pdf) (Medelyan et al., LREC 2006)
ACL
- Olena Medelyan, Stefan Schulz, Jan Paetzold, Michael Poprat, and Kornél Markó. 2006. Language Specific and Topic Focused Web Crawling. In Proceedings of the Fifth International Conference on Language Resources and Evaluation (LREC’06), Genoa, Italy. European Language Resources Association (ELRA).