Latent Dirichlet Allocation with topic-in-set knowledge

  • Authors:
  • David Andrzejewski;Xiaojin Zhu

  • Affiliations:
  • University of Wisconsin-Madison, Madison, WI;University of Wisconsin-Madison, Madison, WI

  • Venue:
  • SemiSupLearn '09 Proceedings of the NAACL HLT 2009 Workshop on Semi-Supervised Learning for Natural Language Processing
  • Year:
  • 2009

Quantified Score

Hi-index 0.00

Visualization

Abstract

Latent Dirichlet Allocation is an unsupervised graphical model which can discover latent topics in unlabeled data. We propose a mechanism for adding partial supervision, called topic-in-set knowledge, to latent topic modeling. This type of supervision can be used to encourage the recovery of topics which are more relevant to user modeling goals than the topics which would be recovered otherwise. Preliminary experiments on text datasets are presented to demonstrate the potential effectiveness of this method.