Accession Number : ADA581247

Title :   IRIT at TREC Microblog 2012: Adhoc Task

Descriptive Note : Conference paper

Corporate Author : TOULOUSE UNIV (FRANCE)

Personal Author(s) : Jabeur, Lamjed B ; Damak, Firas ; Tamine, Lynda ; Pinel-Sauvagnat, Karen ; Cabanac, Guillaume ; Boughanem, Mohand

Full Text : https://apps.dtic.mil/dtic/tr/fulltext/u2/a581247.pdf

Report Date : Nov 2012

Pagination or Media Count : 8

Abstract : This paper describes the participation of the IRIT lab, University of Toulouse France, to the Microblog Track of TREC 2012. Two different models are experimented by our team for the adhoc task: (i) a Bayesian network retrieval model for tweet search and (ii) a feature learning model for relevance classification. Experimental results show that Bayesian network retrieval model improves the performances comparing to the track median.

Descriptors :   *INFORMATION RETRIEVAL , ARTIFICIAL INTELLIGENCE , CLASSIFICATION , FRANCE , MATHEMATICAL MODELS , SYMPOSIA

Subject Categories : Information Science
      Cybernetics

Distribution Statement : APPROVED FOR PUBLIC RELEASE