Powered by OpenAIRE graph
Found an issue? Give us feedback
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ Hyper Article en Lig...arrow_drop_down
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
Hyper Article en Ligne
Other literature type . 2019
HAL-Pasteur
Conference object . 2019
Data sources: HAL-Pasteur
versions View all 4 versions

Des bases de données massives au Web de données : désambiguïsation et alignement d'entités géographiques dans les textes scientifiques

Authors: Cuxac, Pascal; Collignon, Alain; Gregorio, Stéphanie; Parmentier, François;

Des bases de données massives au Web de données : désambiguïsation et alignement d'entités géographiques dans les textes scientifiques

Abstract

Dans cet article nous présentons une approche automatique visant à désambiguïser et aligner des entités géographiques de type placeName. Une méthode basée sur des plongements lexicaux permet, à partir d'un apprentissage non supervisé de lever l'ambiguïté face à un terme polysémique. Cela permet alors un alignement automatique avec différents réservoirs (BNF, wikidata…) possédant un triplestore. Nous utilisons alors les technologies du web sémantique, pour à la fois exposer les données de façon différente (data.istex) mais également autoriser des requêtes complexes impossibles à résoudre à partir de moteurs de recherche classiques. Nous aborderons un cas concret basé sur le réservoir ISTEX, et une évaluation qualitative de la méthode sera proposée.

In this paper we present an automatic approach to disambiguate and align geographic entities. A method based on word embeddings allows, from unsupervised learning, to remove ambiguity with polysemic terms. This allows automatic alignment with different databases (BNF, wikidata...) having a triplestore. We then use semantic web technologies, both to expose the data in a different way (data.istex) but also to allow complex queries that cannot be solved from traditional search engines. We will discuss a concrete case based on the ISTEX database, and a qualitative evaluation of the method will be proposed.

Country
France
Related Organizations
Keywords

Entités géographiques, Automatic alignment, [SHS.INFO]Humanities and Social Sciences/Library and information sciences, Désambiguïsation, Web of Data, Disambiguation, Geographic entities, Données ouvertes liées, Linked Open Data, [SHS.INFO] Humanities and Social Sciences/Library and information sciences, Web de données, Alignement automatique

[2] http://tln.li.univ-tours.fr/Tln_Istex.html [15] https://www.w3.org/2009/08/skos-reference/skos.html Collignon A. & Cuxac P. (2017). ISTEX : des enrichissements au web de donneées. I2D Information, données documents, vol. 54, n° 4, p. 8-15.

Cuxac P. & Thouvenin N. (2017). Archives numeériques et fouille de textes : le projet ISTEX. Atelier TextMine, Conférence EGC'17, Grenoble.

Harlow C. (2015). Data Munging tools in preparation for RDF: Catmandu and LODRefine. Code {4}lib journal, 2015, vol. 30, p. 1-12.

  • BIP!
    Impact byBIP!
    citations
    This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    0
    popularity
    This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
    Average
    influence
    This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    Average
    impulse
    This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
    Average
  • citations
    This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    0
    popularity
    This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
    Average
    influence
    This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    Average
    impulse
    This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
    Average
    Powered byBIP!BIP!
Powered by OpenAIRE graph
Found an issue? Give us feedback
citations
This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Citations provided by BIP!
popularity
This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
BIP!Popularity provided by BIP!
influence
This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Influence provided by BIP!
impulse
This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
BIP!Impulse provided by BIP!
0
Average
Average
Average
Related to Research communities
moresidebar

Do the share buttons not appear? Please make sure, any blocking addon is disabled, and then reload the page.