@inproceedings{ueyama-2006-evaluation,
title = "Evaluation of Web-based Corpora: Effects of Seed Selection and Time Interval",
author = "Ueyama, Motoko",
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/697_pdf.pdf",
abstract = "Recently, there have been efforts to construct written corpora by using the WWW. A promising approach to build Web corpora is to run automated queries to search engines and download pages found in this way. This makes it possible to build corpora rapidly and economically, but we cannot control what are contained in resulting corpora. Under these circumstances, it is important to verify the general nature of Web corpora. This study, in particular, investigated effects of two essential factors on three Japanese corpora that we built: seed terms used for queries; and time interval between different corpus construction sessions, which measures the stability of query results over time. We evaluated the corpora qualitatively, in terms of domains, genres and typical lexical items. Results show these two patterns: 1) both seed selection and time interval affect the distribution of text and lexicon; 2) the effect of seed selection is much stronger. The prominent effect of seed selection suggests that a good understanding of the cause-and-effect relation between seeds and retrieved documents is an important step to gain some control over the characteristics of Web corpora, in particular, for the construction of general corpora meant to represent a language as a whole.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ueyama-2006-evaluation">
<titleInfo>
<title>Evaluation of Web-based Corpora: Effects of Seed Selection and Time Interval</title>
</titleInfo>
<name type="personal">
<namePart type="given">Motoko</namePart>
<namePart type="family">Ueyama</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>Recently, there have been efforts to construct written corpora by using the WWW. A promising approach to build Web corpora is to run automated queries to search engines and download pages found in this way. This makes it possible to build corpora rapidly and economically, but we cannot control what are contained in resulting corpora. Under these circumstances, it is important to verify the general nature of Web corpora. This study, in particular, investigated effects of two essential factors on three Japanese corpora that we built: seed terms used for queries; and time interval between different corpus construction sessions, which measures the stability of query results over time. We evaluated the corpora qualitatively, in terms of domains, genres and typical lexical items. Results show these two patterns: 1) both seed selection and time interval affect the distribution of text and lexicon; 2) the effect of seed selection is much stronger. The prominent effect of seed selection suggests that a good understanding of the cause-and-effect relation between seeds and retrieved documents is an important step to gain some control over the characteristics of Web corpora, in particular, for the construction of general corpora meant to represent a language as a whole.</abstract>
<identifier type="citekey">ueyama-2006-evaluation</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2006/pdf/697_pdf.pdf</url>
</location>
<part>
<date>2006-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Evaluation of Web-based Corpora: Effects of Seed Selection and Time Interval
%A Ueyama, Motoko
%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 ueyama-2006-evaluation
%X Recently, there have been efforts to construct written corpora by using the WWW. A promising approach to build Web corpora is to run automated queries to search engines and download pages found in this way. This makes it possible to build corpora rapidly and economically, but we cannot control what are contained in resulting corpora. Under these circumstances, it is important to verify the general nature of Web corpora. This study, in particular, investigated effects of two essential factors on three Japanese corpora that we built: seed terms used for queries; and time interval between different corpus construction sessions, which measures the stability of query results over time. We evaluated the corpora qualitatively, in terms of domains, genres and typical lexical items. Results show these two patterns: 1) both seed selection and time interval affect the distribution of text and lexicon; 2) the effect of seed selection is much stronger. The prominent effect of seed selection suggests that a good understanding of the cause-and-effect relation between seeds and retrieved documents is an important step to gain some control over the characteristics of Web corpora, in particular, for the construction of general corpora meant to represent a language as a whole.
%U http://www.lrec-conf.org/proceedings/lrec2006/pdf/697_pdf.pdf
Markdown (Informal)
[Evaluation of Web-based Corpora: Effects of Seed Selection and Time Interval](http://www.lrec-conf.org/proceedings/lrec2006/pdf/697_pdf.pdf) (Ueyama, LREC 2006)
ACL