Bayesian feature selection for sparse topic model

Ying Lan Chang*, Kuen Feng Lee, Jen-Tzung Chien

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

5 Scopus citations

Abstract

This paper presents a new Bayesian sparse learning approach to select salient lexical features and build sparse topic model (sTM). The Bayesian learning is performed by incorporating the spike-and-slab priors so that the words with spiky distributions are filtered and those with slab distributions are selected as features for estimating the topic model (TM) based on latent Dirichlet allocation. The variational inference procedure is developed to train sTM parameters. In the experiments on document modeling using TM and sTM, we find that the proposed sTM does not only reduce the model perplexity but also reduce the memory and computation costs. Bayesian feature selection method does effectively identify the representative topic words for building a sparse learning model.

Original languageEnglish
Title of host publication2011 IEEE International Workshop on Machine Learning for Signal Processing - Proceedings of MLSP 2011
DOIs
StatePublished - 5 Dec 2011
Event21st IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2011 - Beijing, China
Duration: 18 Sep 201121 Sep 2011

Publication series

NameIEEE International Workshop on Machine Learning for Signal Processing

Conference

Conference21st IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2011
CountryChina
CityBeijing
Period18/09/1121/09/11

Keywords

  • Bayesian learning
  • feature selection
  • sparse features
  • topic model

Fingerprint Dive into the research topics of 'Bayesian feature selection for sparse topic model'. Together they form a unique fingerprint.

Cite this