• Aucun résultat trouvé

Data Integration through data elements: Mapping data elements to terminological resources

N/A
N/A
Info
Télécharger
Protected

Academic year: 2022

Partager "Data Integration through data elements: Mapping data elements to terminological resources"

Copied!
1
0
0

Chargement.... (Voir le texte intégral maintenant)

Texte intégral

(1)

Data integration through data elements: Mapping data elements to terminological resources

Fleur Mougin EA 3888, IFR 140, Faculté de Médecine, Université de

Rennes I, France fleur.mougin@univ-

rennes1.fr

Anita Burgun EA 3888, IFR 140, Faculté de Médecine, Université de

Rennes I, France anita.burgun@univ-

rennes1.fr

Olivier Bodenreider National Library of Medicine,

Bethesda, Maryland USA

[email protected]

Abstract

Data integration is a crucial task in the biomedical domain. Data elements (DEs) play an important role in data integration and we propose to map DEs to termino- logical resources as an approach to data integration. We extracted DEs from eleven disparate biomedical sources. We compared these DEs to concepts and/or terms in biomedical controlled vocabu- laries and to reference DEs. We also ex- ploited DE values to disambiguate under- specified DEs. Results suggest that data integration can be achieved automatically with limited precision and largely facili- tated by mapping DEs to terminological resources. Finally, the use of general lexical resources and of more powerful techniques to exploit DE values would improve our method.

Références

Télécharger maintenant ( PDF - 1 Page - 43.08 KB )

Documents relatifs

Mapping Keywords to Linked Data Resources for Automatic Query Expansion

[7] argue that matching natural language terms to resources in Linked datasets can easily cross taxonomic boundaries and suggest that expanding the query with a more

Ontology-based Data Integration

As we noted above, the reasoning rules to support ontology for the data in- tegration concept are based on the OPENMath formalism and the algebra of integrable data.. Let the

ShERML: Mapping Relational Data to RDF

We have presented a demo of ShERML, a versatile system for defining mappings from relational databases to RDF with target shape schema using an intuitive and powerful graphical

Data as a Language: A Novel Approach to Data Integration

Con- sequently, the documents serve as input for training vector representations, commonly termed as embed- dings, of data elements (e.g. entire relational tuples or

Ontology-based Data Acccess and Integration: Beyond Relational Data

Ontology-based data access and integration (OBDA/I) are by now well-established paradigms in which users are provided access to one or more data sources through a conceptual view

Geospatial Data Integration and Visualisation Using Linked Data

The substantial improvement of data availability will enable cross- data set analysis and visualisation, in which the integration of geospatial data from different sources

On an Approach to Data Integration: Concept, Formal Foundations and Data Model

As in [5], we also consider the lattice (a partially ordered set) as a relevant con- struction to formalize the hierarchical dimension. The lattice nodes correspond to the units

Elements of a Data-Driven Approach to Adaptation

The proposed case-based inference process can be considered as a kind of transfer learning method since it consists in transferring knowledge learned from the case base to help learn