Duplicate bibliographic record detection with an OCR-converted source of information
Identifieur interne : 000721 ( PascalFrancis/Curation ); précédent : 000720; suivant : 000722Duplicate bibliographic record detection with an OCR-converted source of information
Auteurs : Shoichi Taniguchi [Japon]Source :
- Journal of information science [ 0165-5515 ] ; 2013.
Descripteurs français
- Pascal (Inist)
- Wicri :
- topic : Bibliothèque, Catalogue.
English descriptors
- KwdEn :
Abstract
Duplicate record detection has been an important issue in the fields of data and records management and various detection methods have been proposed. A new method, which uses an optical character recognition (OCR)-converted source of information for record matching to detect duplicates, is proposed and examined in this paper. First, the design of an experiment for examining the perfor- mance of such a duplicate detection method is discussed. The base record set with an OCR-converted title page and its verso were prepared along with two test record sets from different union catalogues, and duplicate records between the base record set and the test sets were manually identified. A duplicate detection system was developed to execute matching (I) between records, (2) between a record and an OCR-converted source of information and (3) using a combination of these. Second, matching performance at the individual data element level is examined. Third, the performance of duplicate record detection based on matching at the element level is examined through rule-based detection and machine learning-based detection. The results of the experiment show the usefulness of incorporating source of information into duplicate detection to a certain extent.
pA |
|
---|
Links toward previous steps (curation, corpus...)
- to stream PascalFrancis, to step Corpus: Pour aller vers cette notice dans l'étape Curation :000047
- to stream PascalFrancis, to step Corpus: Pour aller vers cette notice dans l'étape Curation :000072
Links to Exploration step
Pascal:13-0299709Le document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en" level="a">Duplicate bibliographic record detection with an OCR-converted source of information</title>
<author><name sortKey="Taniguchi, Shoichi" sort="Taniguchi, Shoichi" uniqKey="Taniguchi S" first="Shoichi" last="Taniguchi">Shoichi Taniguchi</name>
<affiliation wicri:level="1"><inist:fA14 i1="01"><s1>School of Library and Information Science, Keio University</s1>
<s3>JPN</s3>
<sZ>1 aut.</sZ>
</inist:fA14>
<country>Japon</country>
</affiliation>
</author>
</titleStmt>
<publicationStmt><idno type="wicri:source">INIST</idno>
<idno type="inist">13-0299709</idno>
<date when="2013">2013</date>
<idno type="stanalyst">PASCAL 13-0299709 INIST</idno>
<idno type="RBID">Pascal:13-0299709</idno>
<idno type="wicri:Area/PascalFrancis/Corpus">000047</idno>
<idno type="stanalyst">FRANCIS 13-0299709 INIST</idno>
<idno type="wicri:Area/PascalFrancis/Corpus">000072</idno>
<idno type="wicri:Area/PascalFrancis/Curation">000721</idno>
</publicationStmt>
<sourceDesc><biblStruct><analytic><title xml:lang="en" level="a">Duplicate bibliographic record detection with an OCR-converted source of information</title>
<author><name sortKey="Taniguchi, Shoichi" sort="Taniguchi, Shoichi" uniqKey="Taniguchi S" first="Shoichi" last="Taniguchi">Shoichi Taniguchi</name>
<affiliation wicri:level="1"><inist:fA14 i1="01"><s1>School of Library and Information Science, Keio University</s1>
<s3>JPN</s3>
<sZ>1 aut.</sZ>
</inist:fA14>
<country>Japon</country>
</affiliation>
</author>
</analytic>
<series><title level="j" type="main">Journal of information science</title>
<title level="j" type="abbreviated">J. inf. sci.</title>
<idno type="ISSN">0165-5515</idno>
<imprint><date when="2013">2013</date>
</imprint>
</series>
</biblStruct>
</sourceDesc>
<seriesStmt><title level="j" type="main">Journal of information science</title>
<title level="j" type="abbreviated">J. inf. sci.</title>
<idno type="ISSN">0165-5515</idno>
</seriesStmt>
</fileDesc>
<profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>Bibliographic reference</term>
<term>Catalogs</term>
<term>Detection</term>
<term>Information source</term>
<term>Library</term>
<term>Optical character recognition</term>
<term>Title</term>
</keywords>
<keywords scheme="Pascal" xml:lang="fr"><term>Référence bibliographique</term>
<term>Détection</term>
<term>Reconnaissance optique caractère</term>
<term>Source information</term>
<term>Bibliothèque</term>
<term>Catalogue</term>
<term>Titre</term>
</keywords>
<keywords scheme="Wicri" type="topic" xml:lang="fr"><term>Bibliothèque</term>
<term>Catalogue</term>
</keywords>
</textClass>
</profileDesc>
</teiHeader>
<front><div type="abstract" xml:lang="en">Duplicate record detection has been an important issue in the fields of data and records management and various detection methods have been proposed. A new method, which uses an optical character recognition (OCR)-converted source of information for record matching to detect duplicates, is proposed and examined in this paper. First, the design of an experiment for examining the perfor- mance of such a duplicate detection method is discussed. The base record set with an OCR-converted title page and its verso were prepared along with two test record sets from different union catalogues, and duplicate records between the base record set and the test sets were manually identified. A duplicate detection system was developed to execute matching (I) between records, (2) between a record and an OCR-converted source of information and (3) using a combination of these. Second, matching performance at the individual data element level is examined. Third, the performance of duplicate record detection based on matching at the element level is examined through rule-based detection and machine learning-based detection. The results of the experiment show the usefulness of incorporating source of information into duplicate detection to a certain extent.</div>
</front>
</TEI>
<inist><standard h6="B"><pA><fA01 i1="01" i2="1"><s0>0165-5515</s0>
</fA01>
<fA02 i1="01"><s0>JISCDI</s0>
</fA02>
<fA03 i2="1"><s0>J. inf. sci.</s0>
</fA03>
<fA05><s2>39</s2>
</fA05>
<fA06><s2>2</s2>
</fA06>
<fA08 i1="01" i2="1" l="ENG"><s1>Duplicate bibliographic record detection with an OCR-converted source of information</s1>
</fA08>
<fA11 i1="01" i2="1"><s1>TANIGUCHI (Shoichi)</s1>
</fA11>
<fA14 i1="01"><s1>School of Library and Information Science, Keio University</s1>
<s3>JPN</s3>
<sZ>1 aut.</sZ>
</fA14>
<fA20><s1>153-168</s1>
</fA20>
<fA21><s1>2013</s1>
</fA21>
<fA23 i1="01"><s0>ENG</s0>
</fA23>
<fA43 i1="01"><s1>INIST</s1>
<s2>14165</s2>
<s5>354000500623560010</s5>
</fA43>
<fA44><s0>0000</s0>
<s1>© 2013 INIST-CNRS. All rights reserved.</s1>
</fA44>
<fA45><s0>27 ref.</s0>
</fA45>
<fA47 i1="01" i2="1"><s0>13-0299709</s0>
</fA47>
<fA60><s1>P</s1>
</fA60>
<fA61><s0>A</s0>
</fA61>
<fA64 i1="01" i2="1"><s0>Journal of information science</s0>
</fA64>
<fA66 i1="01"><s0>GBR</s0>
</fA66>
<fC01 i1="01" l="ENG"><s0>Duplicate record detection has been an important issue in the fields of data and records management and various detection methods have been proposed. A new method, which uses an optical character recognition (OCR)-converted source of information for record matching to detect duplicates, is proposed and examined in this paper. First, the design of an experiment for examining the perfor- mance of such a duplicate detection method is discussed. The base record set with an OCR-converted title page and its verso were prepared along with two test record sets from different union catalogues, and duplicate records between the base record set and the test sets were manually identified. A duplicate detection system was developed to execute matching (I) between records, (2) between a record and an OCR-converted source of information and (3) using a combination of these. Second, matching performance at the individual data element level is examined. Third, the performance of duplicate record detection based on matching at the element level is examined through rule-based detection and machine learning-based detection. The results of the experiment show the usefulness of incorporating source of information into duplicate detection to a certain extent.</s0>
</fC01>
<fC02 i1="01" i2="X"><s0>001A01</s0>
</fC02>
<fC03 i1="01" i2="X" l="FRE"><s0>Référence bibliographique</s0>
<s5>04</s5>
</fC03>
<fC03 i1="01" i2="X" l="ENG"><s0>Bibliographic reference</s0>
<s5>04</s5>
</fC03>
<fC03 i1="01" i2="X" l="SPA"><s0>Referencia bibliográfica</s0>
<s5>04</s5>
</fC03>
<fC03 i1="02" i2="X" l="FRE"><s0>Détection</s0>
<s5>05</s5>
</fC03>
<fC03 i1="02" i2="X" l="ENG"><s0>Detection</s0>
<s5>05</s5>
</fC03>
<fC03 i1="02" i2="X" l="SPA"><s0>Detección</s0>
<s5>05</s5>
</fC03>
<fC03 i1="03" i2="X" l="FRE"><s0>Reconnaissance optique caractère</s0>
<s5>06</s5>
</fC03>
<fC03 i1="03" i2="X" l="ENG"><s0>Optical character recognition</s0>
<s5>06</s5>
</fC03>
<fC03 i1="03" i2="X" l="SPA"><s0>Reconocimento óptico de caracteres</s0>
<s5>06</s5>
</fC03>
<fC03 i1="04" i2="X" l="FRE"><s0>Source information</s0>
<s5>07</s5>
</fC03>
<fC03 i1="04" i2="X" l="ENG"><s0>Information source</s0>
<s5>07</s5>
</fC03>
<fC03 i1="04" i2="X" l="SPA"><s0>Fuente información</s0>
<s5>07</s5>
</fC03>
<fC03 i1="05" i2="X" l="FRE"><s0>Bibliothèque</s0>
<s5>08</s5>
</fC03>
<fC03 i1="05" i2="X" l="ENG"><s0>Library</s0>
<s5>08</s5>
</fC03>
<fC03 i1="05" i2="X" l="SPA"><s0>Biblioteca</s0>
<s5>08</s5>
</fC03>
<fC03 i1="06" i2="X" l="FRE"><s0>Catalogue</s0>
<s5>09</s5>
</fC03>
<fC03 i1="06" i2="X" l="ENG"><s0>Catalogs</s0>
<s5>09</s5>
</fC03>
<fC03 i1="06" i2="X" l="SPA"><s0>Catálogo</s0>
<s5>09</s5>
</fC03>
<fC03 i1="07" i2="X" l="FRE"><s0>Titre</s0>
<s5>10</s5>
</fC03>
<fC03 i1="07" i2="X" l="ENG"><s0>Title</s0>
<s5>10</s5>
</fC03>
<fC03 i1="07" i2="X" l="SPA"><s0>Título</s0>
<s5>10</s5>
</fC03>
<fN21><s1>287</s1>
</fN21>
<fN44 i1="01"><s1>OTO</s1>
</fN44>
<fN82><s1>OTO</s1>
</fN82>
</pA>
</standard>
</inist>
</record>
Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Ticri/CIDE/explor/OcrV1/Data/PascalFrancis/Curation
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 000721 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/PascalFrancis/Curation/biblio.hfd -nk 000721 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien |wiki= Ticri/CIDE |area= OcrV1 |flux= PascalFrancis |étape= Curation |type= RBID |clé= Pascal:13-0299709 |texte= Duplicate bibliographic record detection with an OCR-converted source of information }}
This area was generated with Dilib version V0.6.32. |