N-gram-Based Low-Dimensional Representation for Document Classification.
Rémi LebretRonan CollobertPublished in: ICLR (Workshop) (2015)
Keyphrases
- document classification
- low dimensional
- text categorization
- classification algorithm
- text mining
- web documents
- high dimensional
- text classification
- dimensionality reduction
- topic extraction
- text documents
- natural language
- pattern recognition
- n gram
- databases
- support vector
- knowledge base
- feature selection
- computer vision