Larger Residuals, Less Work: Active Document Scheduling for Latent Dirichlet Allocation.
Mirwaes WahabzadaKristian KerstingPublished in: ECML/PKDD (3) (2011)
Keyphrases
- latent dirichlet allocation
- latent topics
- topic discovery
- lda model
- topic models
- document similarity
- topic extraction
- generative model
- latent dirichlet
- latent semantic analysis
- topic modeling
- text documents
- text mining
- variational bayesian inference
- variational inference
- statistical topic models
- document clustering
- probabilistic latent semantic analysis
- generative process
- gibbs sampling
- document retrieval
- tf idf
- latent topic models
- text analysis
- document classification
- document collections
- information retrieval systems
- dimensionality reduction
- least squares
- information retrieval
- machine learning
- latent variables
- parameter estimation
- word counts
- probabilistic model
- pattern recognition
- maximum likelihood
- hierarchical bayesian model
- data analysis