Word Embedding for Social Book Suggestion

Nawal Ould-Amer 1, 2 Philippe Mulhem 1 Mathias Géry 2 Karam Abdulahhad 1
1 LIG - Laboratoire d'Informatique de Grenoble
2 LHC - Laboratoire Hubert Curien [Saint Etienne]
Abstract : This paper presents the joint work of the Universities of Grenoble and Saint-´ Etienne at CLEF 2016 Social Book Search Suggestion Track. The approaches studied are based on personalization, considering the user's profile in the ranking process. The profile is filtered using Word Embedding, by proposing several ways to handle the generated relationships between terms. We find that tackling the problem of " non-topical " only queries is a great challenge in this case. The official results show that Word Embedding methods are able to improve results in the SBS case.
Keywords : social network word embedding probabilistic retrieval profile selection
Type de document :
Communication dans un congrès
Krisztian Balog, Linda Cappellato, Nicola Ferro, Craig Macdonald. Clef 2016 Conference, Sep 2016, Evora, Portugal. CLEF 2016 Working Notes, 1609, 2016
Liste complète des métadonnées

Littérature citée [11 références]  Voir  Masquer  Télécharger
https://hal-ujm.archives-ouvertes.fr/ujm-01377072
Contributeur : Mathias Géry <>
Soumis le : jeudi 6 octobre 2016 - 11:58:08
Dernière modification le : mercredi 7 novembre 2018 - 13:50:25
Document(s) archivé(s) le : samedi 7 janvier 2017 - 12:53:54

Fichier

word-embedding-social.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : ujm-01377072, version 1

Collections

UNIV-ST-ETIENNE | LIG_SRCPR | LIG | UGA | IOGS | PARISTECH | UNIV-PARIS-SACLAY | LIG_TDCGE_MRIM

Citation

Nawal Ould-Amer, Philippe Mulhem, Mathias Géry, Karam Abdulahhad. Word Embedding for Social Book Suggestion. Krisztian Balog, Linda Cappellato, Nicola Ferro, Craig Macdonald. Clef 2016 Conference, Sep 2016, Evora, Portugal. CLEF 2016 Working Notes, 1609, 2016. 〈ujm-01377072〉

Exporter

BibTeX TEI DC DCterms EndNote

Partager

Métriques

Consultations de la notice

206

Téléchargements de fichiers

153

Contact

support.ccsd.cnrs.fr
hal.support@ccsd.cnrs.fr
Logo CCSD