Toward Word Embedding for Personalized Information Retrieval

Autor: Ould-Amer, Nawal, Mulhem, Philippe, Gery, Mathias

This paper presents preliminary works on using Word Embedding (word2vec) for query expansion in the context of Personalized Information Retrieval. Traditionally, word embeddings are learned on a general corpus, like Wikipedia. In this work we try to

Externí odkaz: http://arxiv.org/abs/1606.06991

Personalized Parsimonious Language Models for User Modeling in Social Bookmaking Systems

Autor: Ould Amer, Nawal, Mulhem, Philippe, Géry, Mathias

Publikováno v: European Conference on Information Retrieval
European Conference on Information Retrieval, Apr 2017, Aberdeen, United Kingdom

International audience; 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 tagge

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::dd106a931a52c40bb07b3f421f711f6e
https://hal-ujm.archives-ouvertes.fr/ujm-01615362/file/2017_10_12_personalized-parsimonious-language_version_finale.pdf

Modèles de Documents Parcimonieux basés sur les annotations et les ' word embeddings ' -Application à la personnalisation

Autor: Ould Amer, Nawal, Mulhem, Philippe, Géry, Mathias

Publikováno v: CORIA 2017-COnférence en Recherche d'Informations et Applications
CORIA 2017-COnférence en Recherche d'Informations et Applications, Mar 2017, Marseille, France

RÉSUMÉ. Nous présentons dans cet article des modèles de langues parcimonieux sociaux de documents qui permettent de détecter les termes les plus importants du document et d'éliminer les termes communs ou non significatifs. La détection de ces

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::8355b9195a718d9113fc1274d51f0c57
https://hal-ujm.archives-ouvertes.fr/ujm-01615862/file/2017_03_21_CORIA2017_paper_21_version_finale.pdf

Word Embedding for Social Book Suggestion

Autor: Ould-Amer, Nawal, Mulhem, Philippe, Géry, Mathias, Abdulahhad, Karam

Publikováno v: CLEF 2016 Working Notes
Clef 2016 Conference
Clef 2016 Conference, Sep 2016, Evora, Portugal

International audience; 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 t

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::fe46133a6f1e22c96cdd9a236f9261e9
https://hal-ujm.archives-ouvertes.fr/ujm-01377072/file/word-embedding-social.pdf

Toward Word Embedding for Personalized Information Retrieval

Autor: Ould Amer, Nawal, Mulhem, Philippe, Géry, Mathias

Publikováno v: Proceedings of the 39th International ACM SIGIR conference on Research and Development in Information Retrieval
Neu-IR: The SIGIR 2016 Workshop on Neural Information Retrieval
Neu-IR: The SIGIR 2016 Workshop on Neural Information Retrieval, Jul 2016, Pisa, Italy

International audience; This paper presents preliminary works on using Word Embedding (word2vec) for query expansion in the context of Personalized Information Retrieval. Traditionally, word em-beddings are learned on a general corpus, like Wikipedia

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e1467e377b9c719e30fa5785e1d21bbf
https://hal-ujm.archives-ouvertes.fr/ujm-01377080