Combining Naive Bayes and n-Gram Language Models for Text Classification.
Fuchun PengDale SchuurmansPublished in: ECIR (2003)
Keyphrases
- text classification
- naive bayes
- n gram
- text categorization
- combining classifiers
- bag of words
- logistic regression
- naive bayes classifier
- feature selection
- text mining
- probability estimation
- machine learning
- text classifiers
- uci datasets
- cost sensitive
- test instances
- uci data sets
- classification algorithm
- document classification
- text data
- unsupervised learning
- bayesian classifier
- text documents
- language modeling
- locally weighted
- bayesian network classifiers
- naive bayesian classifier
- semantic features
- statistical language modeling
- term frequency
- multi label
- unlabeled data
- labeled data
- neural network
- base classifiers
- data sets
- naive bayes classification
- conditional independence assumption
- decision trees
- feature space
- classification accuracy
- bayesian networks
- probabilistic model
- low variance
- probabilistic classifiers
- independence assumption
- knowledge discovery
- information extraction