@inproceedings{wattam-etal-2012-document,
title = "Document Attrition in Web Corpora: an Exploration",
author = "Wattam, Stephen and
Rayson, Paul and
Berridge, Damon",
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 = "http://www.lrec-conf.org/proceedings/lrec2012/pdf/806_Paper.pdf",
pages = "1486--1489",
abstract = "Increases in the use of web data for corpus-building, coupled with the use of specialist, single-use corpora, make for an increasing reliance on language that changes quickly, affecting the long-term validity of studies based on these methods. This drift' through time affects both users of open-source corpora and those attempting to interpret the results of studies based on web data. The attrition of documents online, also called link rot or document half-life, has been studied many times for the purposes of optimising search engine web crawlers, producing robust and reliable archival systems, and ensuring the integrity of distributed information stores, however, the affect that attrition has upon corpora of varying construction remains largely unknown. This paper presents a preliminary investigation into the differences in attrition rate between corpora selected using different corpus construction methods. It represents the first step in a larger longitudinal analysis, and as such presents URI-based content clues, chosen to relate to studies from other areas. The ultimate goal of this larger study is to produce a detailed enumeration of the primary biases online, and identify sampling strategies which control and minimise unwanted effects of document attrition.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wattam-etal-2012-document">
<titleInfo>
<title>Document Attrition in Web Corpora: an Exploration</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stephen</namePart>
<namePart type="family">Wattam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paul</namePart>
<namePart type="family">Rayson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Damon</namePart>
<namePart type="family">Berridge</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>Increases in the use of web data for corpus-building, coupled with the use of specialist, single-use corpora, make for an increasing reliance on language that changes quickly, affecting the long-term validity of studies based on these methods. This drift’ through time affects both users of open-source corpora and those attempting to interpret the results of studies based on web data. The attrition of documents online, also called link rot or document half-life, has been studied many times for the purposes of optimising search engine web crawlers, producing robust and reliable archival systems, and ensuring the integrity of distributed information stores, however, the affect that attrition has upon corpora of varying construction remains largely unknown. This paper presents a preliminary investigation into the differences in attrition rate between corpora selected using different corpus construction methods. It represents the first step in a larger longitudinal analysis, and as such presents URI-based content clues, chosen to relate to studies from other areas. The ultimate goal of this larger study is to produce a detailed enumeration of the primary biases online, and identify sampling strategies which control and minimise unwanted effects of document attrition.</abstract>
<identifier type="citekey">wattam-etal-2012-document</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/806_Paper.pdf</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>1486</start>
<end>1489</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Document Attrition in Web Corpora: an Exploration
%A Wattam, Stephen
%A Rayson, Paul
%A Berridge, Damon
%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 wattam-etal-2012-document
%X Increases in the use of web data for corpus-building, coupled with the use of specialist, single-use corpora, make for an increasing reliance on language that changes quickly, affecting the long-term validity of studies based on these methods. This drift’ through time affects both users of open-source corpora and those attempting to interpret the results of studies based on web data. The attrition of documents online, also called link rot or document half-life, has been studied many times for the purposes of optimising search engine web crawlers, producing robust and reliable archival systems, and ensuring the integrity of distributed information stores, however, the affect that attrition has upon corpora of varying construction remains largely unknown. This paper presents a preliminary investigation into the differences in attrition rate between corpora selected using different corpus construction methods. It represents the first step in a larger longitudinal analysis, and as such presents URI-based content clues, chosen to relate to studies from other areas. The ultimate goal of this larger study is to produce a detailed enumeration of the primary biases online, and identify sampling strategies which control and minimise unwanted effects of document attrition.
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/806_Paper.pdf
%P 1486-1489
Markdown (Informal)
[Document Attrition in Web Corpora: an Exploration](http://www.lrec-conf.org/proceedings/lrec2012/pdf/806_Paper.pdf) (Wattam et al., LREC 2012)
ACL
- Stephen Wattam, Paul Rayson, and Damon Berridge. 2012. Document Attrition in Web Corpora: an Exploration. In Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC'12), pages 1486–1489, Istanbul, Turkey. European Language Resources Association (ELRA).