SDRS: A new lossless dimensionality reduction for text corpora.
Iñaki Vélez de MendizabalVítor Basto FernandesEnaitz EzpeletaJosé Ramon MéndezUrko ZurutuzaPublished in: Inf. Process. Manag. (2020)
Keyphrases
- text corpora
- dimensionality reduction
- text mining
- text analysis
- high dimensional data
- low dimensional
- computational linguistics
- principal component analysis
- high dimensional
- feature extraction
- data points
- document collections
- pattern recognition
- topic models
- concept hierarchy
- text classifiers
- feature selection
- text documents
- topic modeling
- feature space
- machine learning
- text collections
- databases
- probabilistic model
- face recognition