Reinforcing the Topic of Embeddings with Theta Pure Dependence for Text Classification.
Ning XingYuexian HouPeng ZhangWenjie LiDawei SongPublished in: EMNLP (2015)
Keyphrases
- text classification
- classifying web pages
- topic discovery
- text mining
- naive bayes
- bag of words
- text categorization
- feature selection
- machine learning
- n gram
- sentiment analysis
- dimensionality reduction
- text data
- vector space
- text classifiers
- semantic features
- document classification
- euclidean space
- text documents
- labeled data
- low dimensional
- worst case
- news articles
- latent dirichlet allocation
- knn
- information extraction
- probabilistic model
- multi label
- sentiment classification
- document set
- natural language processing