Supervised topic classification for modeling a hierarchical conference structure - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2015

Supervised topic classification for modeling a hierarchical conference structure

Résumé

In this paper we investigate the problem of supervised latent modelling for extracting topic hierarchies from data. The supervised part is given in the form of expert information over document-topic correspondence. To exploit the expert information we use a regularization term that penalizes the difference between a predicted and an expert-given model. We hence add the regularization term to the log-likelihood function and use a stochastic EM based algorithm for parameter estimation. The proposed method is used to construct a topic hierarchy over the proceedings of the European Conference on Operational Research and helps to automatize the abstract submission system.
Fichier non déposé

Dates et versions

hal-01236585 , version 1 (01-12-2015)

Identifiants

Citer

Mikhail Kuznetsov, Marianne Clausel, Massih-Reza Amini, Eric Gaussier, Vadim Strijov. Supervised topic classification for modeling a hierarchical conference structure. 22nd International Conference on Neural Information Processing (ICONIP 2015), Nov 2015, Istanbul, Turkey. pp.90-97, ⟨10.1007/978-3-319-26532-2_11⟩. ⟨hal-01236585⟩
272 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More