Personalized Parsimonious Language Models for User Modeling in Social Bookmaking Systems - Université Jean-Monnet-Saint-Étienne Accéder directement au contenu
Communication Dans Un Congrès Année : 2017

Personalized Parsimonious Language Models for User Modeling in Social Bookmaking Systems

Résumé

This paper focuses on building accurate profiles of users, based on bookmarking systems. To achieve this goal, we define personalized parsimonious language models that employ three main resources: the tags, the documents tagged by the user and word embeddings that handle general knowledge. Experiments completed on Delicious data show that our proposal outperforms state-of-the-art approaches and non-personalized parsimonious models.
Fichier principal
Vignette du fichier
2017_10_12_personalized-parsimonious-language_version_finale.pdf (309.99 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

ujm-01615362 , version 1 (12-10-2017)

Identifiants

  • HAL Id : ujm-01615362 , version 1

Citer

Nawal Ould Amer, Philippe Mulhem, Mathias Géry. Personalized Parsimonious Language Models for User Modeling in Social Bookmaking Systems. European Conference on Information Retrieval, Apr 2017, Aberdeen, United Kingdom. ⟨ujm-01615362⟩
237 Consultations
353 Téléchargements

Partager

Gmail Facebook X LinkedIn More