A Semi-supervised Hidden Markov Topic Model Based on Prior Knowledge.
Sattar SeifollahiMassimo PiccardiEhsan Zare BorzeshiPublished in: AusDM (2017)
Keyphrases
- semi supervised
- prior knowledge
- labeled data
- unlabeled data
- semi supervised learning
- generative model
- mixture model
- domain knowledge
- co training
- prior information
- unsupervised learning
- semi supervised classification
- multi view
- active learning
- bayesian framework
- supervised learning
- topic models
- multi document summarization
- semi supervised clustering
- tree models
- data sets
- incorporation of prior knowledge
- manifold learning
- pairwise
- shape prior
- topic modeling
- background knowledge
- maximum likelihood
- co occurrence
- topic specific
- constrained clustering
- related topics
- training data