 |
Université Jean Monnet – Saint-Etienne |  |
Conference papers
Personalized Parsimonious Language Models for User Modeling in Social Bookmaking Systems
Abstract : 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.
Cited literature [13 references]
https://hal-ujm.archives-ouvertes.fr/ujm-01615362
Contributor : Mathias Géry <>
Submitted on : Thursday, October 12, 2017 - 12:08:13 PM
Last modification on : Wednesday, October 7, 2020 - 3:02:36 AM
Contributor : Mathias Géry <>
Submitted on : Thursday, October 12, 2017 - 12:08:13 PM
Last modification on : Wednesday, October 7, 2020 - 3:02:36 AM
File
2017_10_12_personalized-parsim...
Files produced by the author(s)