IRIT at TREC 2014 Contextual Suggestion Track

Bilel Moulahi (1, 2) , Lynda Tamine (1) , Sadok Ben Yahia (2)

1 IRIT-SIG - Systèmes d’Informations Généralisées
2 Laboratoire d'Informatique, Programmation, Algorithmique et Heuristique - LIPAH (Tunis, Tunisie)

In this work, we give an overview of our participation in the TREC 2014 Contextual Suggestion Track. To address the retrieval of attraction places, we propose a fuzzy-based document combination approach for preference learning and context processing.We use the open web in our submission and make use of both criteria users preferences and geographical location criteria.

Mots clés: Contextual suggestion track

Domaines: Théorie de l'information [cs.IT]; Recherche d'information [cs.IR]

Bilel Moulahi, Lynda Tamine, Sadok Ben Yahia. IRIT at TREC 2014 Contextual Suggestion Track. 33th Text REtrieval Conference (TREC 2014), Nov 2014, Gaithersburg, Maryland, United States. pp. 1-4. ⟨hal-01360877⟩