Reading Contexts for Structured Documents Retrieval

Abstract : This paper focuses on the retrieval of parts of structured document called doxels. We propose a notion of reading context of a doxel and we exploit it to extend an Indexing Language Model (LM) with Dirichlet smoothing. We interpret a context of a doxel as a propagation of the content of the connected doxels via document structure links. We experiment this model on INEX corpus 2009, and test different context propagations. We measure a significant increase in results using contexts, compared to a reference approach without the use of context for 3 types of doxels. Moreover, our proposal outperforms the best result obtained for the Focused evaluation for the Ad Hoc task at INEX 2009.
Type de document :
Communication dans un congrès
OAIR, 2013, Lisbon, Portugal. pp.47-52, 2013
Liste complète des métadonnées
Contributeur : Marie-Christine Fauvet <>
Soumis le : vendredi 28 février 2014 - 10:31:39
Dernière modification le : mercredi 7 novembre 2018 - 13:32:03


  • HAL Id : hal-00953082, version 1



Philippe Mulhem, Jean-Pierre Chevallet. Reading Contexts for Structured Documents Retrieval. OAIR, 2013, Lisbon, Portugal. pp.47-52, 2013. 〈hal-00953082〉



Consultations de la notice