How ontology based information retrieval systems may benefit from lexical text analysis - IMT - Institut Mines-Télécom Accéder directement au contenu
Chapitre D'ouvrage Année : 2013

How ontology based information retrieval systems may benefit from lexical text analysis

Résumé

The exponential growth of available electronic data is almost useless without efficient tools to retrieve the right information at the right time. It is now widely acknowledged that information retrieval systems need to take semantics into account to enhance the use of available information. However, there is still a gap between the amounts of relevant information that can be accessed through optimized IRSs on the one hand, and users' ability to grasp and process a handful of relevant data at once on the other. This chapter shows how conceptual and lexical approaches may be jointly used to enrich document description. After a survey on semantic based methodologies designed to efficiently retrieve and exploit information, hybrid approaches are discussed. The original approach presented here benefits from both lexical and ontological document description, and combines them in a software architecture dedicated to information retrieval and rendering in specific domains.
Fichier principal
Vignette du fichier
Ontolex_RanwezEtAl_chapter.pdf (459.96 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-00797143 , version 1 (05-03-2013)

Identifiants

  • HAL Id : hal-00797143 , version 1
  • PRODINRA : 190765

Citer

Sylvie Ranwez, Benjamin Duthil, Mohameth-François Sy, Jacky Montmain, Patrick Augereau, et al.. How ontology based information retrieval systems may benefit from lexical text analysis. Oltramari, Alessandro; Vossen, Piek; Qin, Lu; Hovy, Eduard. New Trends of Research in Ontologies and Lexical Resources, 15, Springer, pp.209-230, 2013, Theory and Applications of Natural Language Processing, 978-3-642-31781-1. ⟨hal-00797143⟩
424 Consultations
1353 Téléchargements

Partager

Gmail Facebook X LinkedIn More