Supervised topic classification for modeling a hierarchical conference structure

Mikhail Kuznetsov; Marianne Clausel; Massih-Reza Amini; Eric Gaussier; Vadim Strijov

doi:10.1007/978-3-319-26532-2_11

Supervised topic classification for modeling a hierarchical conference structure

Mikhail Kuznetsov ¹ Marianne Clausel ² Massih-Reza Amini ³ Eric Gaussier ³ Vadim Strijov ¹

1 MIPT - Moscow Institute of Physics and Technology [Moscow]

2 SAM - Statistique Apprentissage Machine

LJK - Laboratoire Jean Kuntzmann

3 AMA - Analyse de données, Modélisation et Apprentissage automatique [Grenoble]

LIG - Laboratoire d'Informatique de Grenoble

Abstract : 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.

Keywords : hierarchical topic model labeled classification probabilistic latent semantic analysis EM approach

Document type :

Conference papers

Domain :

Computer Science [cs] / Machine Learning [cs.LG]

Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-01236585
Contributor : Massih-Reza Amini <>
Submitted on : Tuesday, December 1, 2015 - 9:29:06 PM
Last modification on : Thursday, October 11, 2018 - 8:48:05 AM

Mikhail Kuznetsov, Marianne Clausel, Massih-Reza Amini, Eric Gaussier, Vadim Strijov. Supervised topic classification for modeling a hierarchical conference structure. Sabri Arik; Tingwen Huang; Weng Kin Lai; Qingshan Liu. 22nd International Conference on Neural Information Processing (ICONIP 2015), Nov 2015, Istanbul, Turkey. Springer, 9489 (Part I), pp.90-97, 2015, Lecture Notes in Computer Science. 〈http://www.iconip2015.org/〉. 〈10.1007/978-3-319-26532-2_11〉. 〈hal-01236585〉

Supervised topic classification for modeling a hierarchical conference structure

Identifiers

Collections

Citation

Export

Metrics

466

Contact

Supervised topic classification for modeling a hierarchical conference structure

Identifiers

Collections

Citation

Export

Share

Metrics

466

Contact