Skip to Main content Skip to Navigation
Conference papers

Exploitation des connaissances d'UMLS pour la recherche d'information médicale. Vers un modèle bayésien d'indexation

Abstract : Knowledge-based information retrieval is widely exploited, but still not very well successful. In this paper, we aim to study the impact of explorations of a knowledge source, named UMLS meta-thesaurus, in medical domain information retrieval. The integration of semantic labels of concepts in a multi-layer indexing proves quite encouraging results in ImageCLEF 2006 evaluation forum. In order to reach a more semantic rich information retrieval system, we tend to explore the hierarchy relationships between concepts in UMLS. For this purpose, we propose a Bayesian network based model to capture the general-specific links between query concepts and documents concepts.
Document type :
Conference papers
Complete list of metadata

Cited literature [9 references]  Display  Hide  Download

https://hal.inria.fr/hal-00954035
Contributor : Marie-Christine Fauvet <>
Submitted on : Monday, March 3, 2014 - 12:17:21 PM
Last modification on : Tuesday, December 8, 2020 - 10:42:35 AM
Long-term archiving on: : Saturday, May 31, 2014 - 10:52:34 AM

File

RJCRI_Diem.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-00954035, version 1

Collections

Citation

Thi Hoang Diem Le. Exploitation des connaissances d'UMLS pour la recherche d'information médicale. Vers un modèle bayésien d'indexation. RJCRI, 2007, Saint-Etienne, France. ⟨hal-00954035⟩

Share

Metrics

Record views

208

Files downloads

225