Skip to Main content Skip to Navigation
Conference papers

Évaluation de la pertinence dans les moteurs de recherche géoréférencés

Abstract : Learning to rank documents on a search engine requires relevance judgments. We introduce the results of an innovating study on relevance modeling for local search engines. These search engines present search results on a map or as a list of maps. Each map contains all the attributes of a place (noun, address, phone number, etc). Most of these attributes are links users can click. We model the relevance as the weighted sum of all the clicks on a result. We obtain good results by fixing the same weight for each component of the model. We propose a relative order between clicks to determine the optimal weights.
Document type :
Conference papers
Complete list of metadata

Cited literature [19 references]  Display  Hide  Download

https://hal.inria.fr/hal-01259542
Contributor : Léa Laporte <>
Submitted on : Wednesday, January 20, 2016 - 3:45:18 PM
Last modification on : Wednesday, June 9, 2021 - 1:10:04 PM
Long-term archiving on: : Friday, November 11, 2016 - 1:31:40 PM

File

2012_INFORSID_LL_LC_SD_JM.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01259542, version 1

Citation

Léa Laporte, Laurent Candillier, Sébastien Dejean, Josiane Mothe. Évaluation de la pertinence dans les moteurs de recherche géoréférencés. INFormatique des Organisations et Systemes d'Information et de Decision (INFORSID 2012), May 2012, Montpellier, France. pp.16. ⟨hal-01259542⟩

Share

Metrics

Record views

168

Files downloads

257