@inproceedings{eckart-etal-2012-influence,
title = "The Influence of Corpus Quality on Statistical Measurements on Language Resources",
author = "Eckart, Thomas and
Quasthoff, Uwe and
Goldhahn, Dirk",
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/476_Paper.pdf",
pages = "2318--2321",
abstract = "The quality of statistical measurements on corpora is strongly related to a strict definition of the measuring process and to corpus quality. In the case of multiple result inspections, an exact measurement of previously specified parameters ensures compatibility of the different measurements performed by different researchers on possibly different objects. Hence, the comparison of different values requires an exact description of the measuring process. To illustrate this correlation the influence of different definitions for the concepts ''''''``word'''''''' and ''''''``sentence'''''''' is shown for several properties of large text corpora. It is also shown that corpus pre-processing strongly influences corpus size and quality as well. As an example near duplicate sentences are identified as source of many statistical irregularities. The problem of strongly varying results especially holds for Web corpora with a large set of pre-processing steps. Here, a well-defined and language independent pre-processing is indispensable for language comparison based on measured values. Conversely, irregularities found in such measurements are often a result of poor pre-processing and therefore such measurements can help to improve corpus quality.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="eckart-etal-2012-influence">
<titleInfo>
<title>The Influence of Corpus Quality on Statistical Measurements on Language Resources</title>
</titleInfo>
<name type="personal">
<namePart type="given">Thomas</namePart>
<namePart type="family">Eckart</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Uwe</namePart>
<namePart type="family">Quasthoff</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dirk</namePart>
<namePart type="family">Goldhahn</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>The quality of statistical measurements on corpora is strongly related to a strict definition of the measuring process and to corpus quality. In the case of multiple result inspections, an exact measurement of previously specified parameters ensures compatibility of the different measurements performed by different researchers on possibly different objects. Hence, the comparison of different values requires an exact description of the measuring process. To illustrate this correlation the influence of different definitions for the concepts ”””“word”””” and ”””“sentence”””” is shown for several properties of large text corpora. It is also shown that corpus pre-processing strongly influences corpus size and quality as well. As an example near duplicate sentences are identified as source of many statistical irregularities. The problem of strongly varying results especially holds for Web corpora with a large set of pre-processing steps. Here, a well-defined and language independent pre-processing is indispensable for language comparison based on measured values. Conversely, irregularities found in such measurements are often a result of poor pre-processing and therefore such measurements can help to improve corpus quality.</abstract>
<identifier type="citekey">eckart-etal-2012-influence</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/476_Paper.pdf</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>2318</start>
<end>2321</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The Influence of Corpus Quality on Statistical Measurements on Language Resources
%A Eckart, Thomas
%A Quasthoff, Uwe
%A Goldhahn, Dirk
%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 eckart-etal-2012-influence
%X The quality of statistical measurements on corpora is strongly related to a strict definition of the measuring process and to corpus quality. In the case of multiple result inspections, an exact measurement of previously specified parameters ensures compatibility of the different measurements performed by different researchers on possibly different objects. Hence, the comparison of different values requires an exact description of the measuring process. To illustrate this correlation the influence of different definitions for the concepts ”””“word”””” and ”””“sentence”””” is shown for several properties of large text corpora. It is also shown that corpus pre-processing strongly influences corpus size and quality as well. As an example near duplicate sentences are identified as source of many statistical irregularities. The problem of strongly varying results especially holds for Web corpora with a large set of pre-processing steps. Here, a well-defined and language independent pre-processing is indispensable for language comparison based on measured values. Conversely, irregularities found in such measurements are often a result of poor pre-processing and therefore such measurements can help to improve corpus quality.
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/476_Paper.pdf
%P 2318-2321
Markdown (Informal)
[The Influence of Corpus Quality on Statistical Measurements on Language Resources](http://www.lrec-conf.org/proceedings/lrec2012/pdf/476_Paper.pdf) (Eckart et al., LREC 2012)
ACL