Topic Modeling with Nonparametric Markov Tree.
Haojun Chen, David B. Dunson, Lawrence Carin · PubMed · 2011
) parsimonious sub-topics are manifested, by removing redundant usage of words at multiple scales. The depth and width of the tree are unbounded within the prior, with a retrospective sampler employed to adaptively infer the appropriate tree size based upon the corpus under study. Excellent quantitative results are manifested on five standard data sets, and the inferred tree structure is also found to be highly interpretable.