A hybrid unsupervised approach for document clustering.
Mihai SurdeanuJordi TurmoAlicia AgenoPublished in: KDD (2005)
Keyphrases
- document clustering
- text mining
- document collections
- document representation
- clustering algorithm
- negative matrix factorization
- clustering method
- topic extraction
- document clusters
- vector space model
- semi supervised
- cluster analysis
- text documents
- tolerance rough set
- document corpus
- clustering quality
- clustering approaches
- information retrieval
- machine learning
- unsupervised learning
- supervised learning
- pairwise constraints
- image features
- training set
- metadata