Interpretable Low-rank Document Representations with Label-dependent Sparsity Patterns.
Ivan IvekPublished in: DMNLP@PKDD/ECML (2014)
Keyphrases
- low rank
- document representation
- linear combination
- missing data
- convex optimization
- matrix completion
- matrix factorization
- regularized regression
- singular value decomposition
- high dimensional data
- semi supervised
- document collections
- high order
- data fusion
- vector space
- document clustering
- vector space model
- high dimensional
- bag of words
- computer vision
- semantic information
- object recognition
- text documents
- sparse representation
- text mining
- active learning
- multiscale