Léa Laporte

Learn More
Feature selection in learning to rank has recently emerged as a crucial issue. Whereas several preprocessing approaches have been proposed, only a few have focused on integrating feature selection into the learning process. In this paper, we propose a general framework for feature selection in learning to rank using support vector machines with a sparse(More)
RÉSUMÉ. Optimiser le classement des résultats d’un moteur par un algorithme de learning to rank nécessite de connaître des jugements de pertinence entre requêtes et documents. Nous présentons les résultats d’une étude pilote sur la modélisation de la pertinence dans les moteurs de recherche géoréférencés. La particularité de ces moteurs est de présenter les(More)
This paper presents a novel document relevance model based on clickthrough information. Compared to the models from the literature we consider the case when documents can be clicked several times in a given search session. This case occurs more and more frequently, specifically for multi-clickable documents such as maps in location search enginess.(More)
Learning to rank algorithms are dealing with a very large amount of features to automatically learn ranking functions, which leads to an increase of both the computational cost and the number of noisy redundant features. Feature selection is seen as a promising way to address these issues. In this paper, we propose new feature selection algorithms for(More)
The amount of social events has increased significantly and location-based services have become an integral part of our life. This makes the recommendation of activity sequences an important emerging application. Recently, the notion of a distributed event (e.g. festival or cruise) that gathers multiple competitive activities has appeared in the literature.(More)
Several private Web search solutions have been proposed to preserve the user privacy while querying search engines. However, most of these solutions are costly in term of processing, network overhead and latency as they mostly rely on cryptographic techniques and/or the generation of fake requests. Furthermore, all these solutions protect all queries(More)
RÉSUMÉ. Sélectionner les caractéristiques les plus utiles et les moins redondantes au sein des fonctions d’ordonnancement et réduire les temps d’exécution sont des enjeux en apprentissage d’ordonnancement. Les algorithmes de sélection de variables basés sur les SVM régularisés sont des approches prometteuses dans ce cadre. Dans cet article, nous proposons(More)
As amount of activities available for users and their variety have grown, personalised recommendation of activities sequences has become an important challenge. However, most of recommender systems do not consider temporal constraints of activities, making the recommendation hard for user to follow. In this article, we describe a novel approach for(More)
Vacations and leisure activities constitute an important part of human life. Nowadays, a lot of attention is paid to cruising, that is reported to be a favourite vacation choice for families with kids and for Millenials. Like other distributed events (events that gather multiple activities distributed in space and time under one umbrella) such as big(More)