Bibliography References Validation using Emergent Architecture
Identifieur interne : 003130 ( Crin/Checkpoint ); précédent : 003129; suivant : 003131Bibliography References Validation using Emergent Architecture
Auteurs : F. Parmentier ; Abdel Belaïd [France]Source :
English descriptors
- KwdEn :
Abstract
In this paper, we present an AI approach for the semantic recognition of bibliography references. The objectif is to produce for each reference a structured flow containing, in UNIMARG format, the list of the different sub-fields recognized and semantically validated. References are given by an OCR flow in SGML format. For the component recognition, we use a generic model of a reference class and an approach based on hypotheses production and verification about component limits in the reference area. Once limits are found, each component is validated according to the relationships between its terms (for example, co-authors) and between terms within different components (for example, relationships between authors and keywords (themes) in the title). These relationships are validated from references written by the same authors or by authors in close domains and located in a reference data base. We use an emergent architecture based on a Concept Network. The Concept Network is dynamic\, ; it allows concepts and, consequently, ``agents'' to emerge. This new architecture is experimented on some paper references belonging to our laboratory references.
Links toward previous steps (curation, corpus...)
Links to Exploration step
CRIN:parmentier94bLe document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en" wicri:score="189">Bibliography References Validation using Emergent Architecture</title>
</titleStmt>
<publicationStmt><idno type="RBID">CRIN:parmentier94b</idno>
<date when="1994" year="1994">1994</date>
<idno type="wicri:Area/Crin/Corpus">001624</idno>
<idno type="wicri:Area/Crin/Curation">001624</idno>
<idno type="wicri:explorRef" wicri:stream="Crin" wicri:step="Curation">001624</idno>
<idno type="wicri:Area/Crin/Checkpoint">003130</idno>
<idno type="wicri:explorRef" wicri:stream="Crin" wicri:step="Checkpoint">003130</idno>
</publicationStmt>
<sourceDesc><biblStruct><analytic><title xml:lang="en">Bibliography References Validation using Emergent Architecture</title>
<author><name sortKey="Parmentier, F" sort="Parmentier, F" uniqKey="Parmentier F" first="F." last="Parmentier">F. Parmentier</name>
</author>
<author><name sortKey="Belaid, A" sort="Belaid, A" uniqKey="Belaid A" first="A." last="Belaïd">Abdel Belaïd</name>
<affiliation><country>France</country>
<placeName><settlement type="city">Nancy</settlement>
<region type="region" nuts="2">Grand Est</region>
<region type="region" nuts="2">Lorraine (région)</region>
</placeName>
<orgName type="laboratoire" n="5">Laboratoire lorrain de recherche en informatique et ses applications</orgName>
<orgName type="university">Université de Lorraine</orgName>
<orgName type="institution">Centre national de la recherche scientifique</orgName>
<orgName type="institution">Institut national de recherche en informatique et en automatique</orgName>
</affiliation>
</author>
</analytic>
</biblStruct>
</sourceDesc>
</fileDesc>
<profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>bibliography reference</term>
<term>emergent architecture</term>
<term>knowledge database</term>
<term>semantic validation</term>
<term>stochastic learning</term>
</keywords>
</textClass>
</profileDesc>
</teiHeader>
<front><div type="abstract" xml:lang="en" wicri:score="3013">In this paper, we present an AI approach for the semantic recognition of bibliography references. The objectif is to produce for each reference a structured flow containing, in UNIMARG format, the list of the different sub-fields recognized and semantically validated. References are given by an OCR flow in SGML format. For the component recognition, we use a generic model of a reference class and an approach based on hypotheses production and verification about component limits in the reference area. Once limits are found, each component is validated according to the relationships between its terms (for example, co-authors) and between terms within different components (for example, relationships between authors and keywords (themes) in the title). These relationships are validated from references written by the same authors or by authors in close domains and located in a reference data base. We use an emergent architecture based on a Concept Network. The Concept Network is dynamic\, ; it allows concepts and, consequently, ``agents'' to emerge. This new architecture is experimented on some paper references belonging to our laboratory references.</div>
</front>
</TEI>
<BibTex type="inproceedings"><ref>parmentier94b</ref>
<crinnumber>94-R-251</crinnumber>
<category>3</category>
<equipe>READ</equipe>
<author><e>Parmentier, F.</e>
<e>Belaïd, A.</e>
</author>
<title>Bibliography References Validation using Emergent Architecture</title>
<booktitle>{Proceedings International Conference on Document Analysis and Recognition, Montréal (Canada)}</booktitle>
<year>1994</year>
<volume>2</volume>
<pages>532-535</pages>
<month>aug</month>
<keywords><e>bibliography reference</e>
<e>emergent architecture</e>
<e>knowledge database</e>
<e>stochastic learning</e>
<e>semantic validation</e>
</keywords>
<abstract>In this paper, we present an AI approach for the semantic recognition of bibliography references. The objectif is to produce for each reference a structured flow containing, in UNIMARG format, the list of the different sub-fields recognized and semantically validated. References are given by an OCR flow in SGML format. For the component recognition, we use a generic model of a reference class and an approach based on hypotheses production and verification about component limits in the reference area. Once limits are found, each component is validated according to the relationships between its terms (for example, co-authors) and between terms within different components (for example, relationships between authors and keywords (themes) in the title). These relationships are validated from references written by the same authors or by authors in close domains and located in a reference data base. We use an emergent architecture based on a Concept Network. The Concept Network is dynamic\, ; it allows concepts and, consequently, ``agents'' to emerge. This new architecture is experimented on some paper references belonging to our laboratory references.</abstract>
</BibTex>
</record>
Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Wicri/Lorraine/explor/InforLorV4/Data/Crin/Checkpoint
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 003130 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Crin/Checkpoint/biblio.hfd -nk 003130 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien |wiki= Wicri/Lorraine |area= InforLorV4 |flux= Crin |étape= Checkpoint |type= RBID |clé= CRIN:parmentier94b |texte= Bibliography References Validation using Emergent Architecture }}
![]() | This area was generated with Dilib version V0.6.33. | ![]() |