Text classification by untrained sentence embeddings.
Daniele Di SarliClaudio GallicchioAlessio MicheliPublished in: Intelligenza Artificiale (2020)
Keyphrases
- text classification
- training corpus
- linguistic features
- text representation
- text categorization
- bag of words
- n gram
- text mining
- machine learning
- natural language
- feature selection
- naive bayes
- document classification
- text documents
- part of speech
- sentiment classification
- euclidean space
- labeled data
- knn
- text data
- low dimensional
- dimensionality reduction
- sentence level
- feature extraction
- multi label
- sentiment analysis
- language modeling
- distance measure
- text classifiers
- manifold learning
- rough sets
- semantic features
- data cleaning
- similarity measure
- classification accuracy