HarpLDA+: Optimizing latent dirichlet allocation for parallel efficiency.
Bo PengBingjing ZhangLangshi ChenMihai AvramRobert HenschelCraig A. StewartShaojuan ZhuEmily McCallumLisa SmithTom ZahniserJon OmerJudy QiuPublished in: IEEE BigData (2017)
Keyphrases
- latent dirichlet allocation
- topic models
- topic modeling
- generative model
- probabilistic latent semantic indexing
- topic discovery
- variational bayesian inference
- gibbs sampling
- probabilistic topic models
- variational inference
- latent topic models
- probabilistic latent semantic analysis
- lda model
- prior knowledge
- latent variables
- latent topics
- dimensionality reduction
- text documents
- bayesian networks
- text mining
- hierarchical bayesian model
- word counts
- hidden markov models