Partitioning and Matching Tuning of Large Biomedical Ontologies - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2018

Partitioning and Matching Tuning of Large Biomedical Ontologies

Résumé

Large biomedical ontologies such as SNOMED CT, NCI, and FMA are exten-sively employed in the biomedical domain. These complex ontologies are basedon diverse modelling views and vocabularies. We define an approach that breaksup a large ontology alignment problem into a set of smaller matching tasks.We coupled this approach with an automated tuning process, which generatesthe adequate thresholds of the available similarity measure for any biomedicalmatching task. Experiments demonstrate that the coupling between ontologypartitioning and threshold tuning outperforms the existing approaches.

Mots clés

Fichier principal
Vignette du fichier
laadhar_22528.pdf (405.56 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02181942 , version 1 (12-07-2019)

Identifiants

  • HAL Id : hal-02181942 , version 1
  • OATAO : 22528

Citer

Amir Laadhar, Faiza Ghozzi, Ryutaro Ichise, Imen Megdiche, Franck Ravat, et al.. Partitioning and Matching Tuning of Large Biomedical Ontologies. 13th International Workshop on Ontology Matching co-located with the 17th International Semantic Web Conference (OM 2018), Oct 2018, Monterey, CA, United States. pp.220-221. ⟨hal-02181942⟩
53 Consultations
23 Téléchargements

Partager

Gmail Facebook X LinkedIn More