ACL RD-TEC 1.0 Summarization of W03-0417
Paper Title:
TRAINING A NAIVE BAYES CLASSIFIER VIA THE EM ALGORITHM WITH A CLASS DISTRIBUTION CONSTRAINT
TRAINING A NAIVE BAYES CLASSIFIER VIA THE EM ALGORITHM WITH A CLASS DISTRIBUTION CONSTRAINT
Authors: Yoshimasa Tsuruoka and Jun'ichi Tsujii
Primarily assigned technology terms:
- adaboost
- algorithm
- bayes classifier
- binary classification
- classification
- classifier
- classifiers
- co-training
- disambiguation
- disambiguation problem
- em algorithm
- expectation maximization
- gibbs sampling
- image recognition
- information processing
- information retrieval
- language processing
- learning
- learning algorithm
- learning algorithms
- learning process
- learning techniques
- machine learning
- machine learning techniques
- maximum entropy
- maximum likelihood
- naive bayes
- naive bayes classifier
- natural language processing
- nlp
- processing
- recognition
- sampling
- semantic disambiguation
- sense disambiguation
- set disambiguation
- smoothing
- smoothing method
- smoothing technique
- spelling
- spelling correction
- supervised learning
- support vector machines
- text classification
- training process
- unsupervised learning
- weighting
- word sense disambiguation
Other assigned terms:
- annotation
- approach
- baseline performance
- bayes model
- binary feature
- case
- class distribution
- class probability
- classification error
- classification performance
- conditional independence
- context features
- convergence
- corpora
- data sets
- discourse
- distribution
- entropy
- entropy models
- estimation
- experimental results
- fact
- feature
- feature vector
- grammars
- implementation
- labeled training data
- language processing tasks
- large corpus
- likelihood
- local context
- maximum entropy models
- meaning
- method
- naive bayes model
- natural language
- natural language processing tasks
- nlp applications
- polysemous word
- polysemous words
- precision
- probability
- probability model
- process
- processing tasks
- semantic
- sense disambiguation problem
- sentence
- sigmoid function
- statistics
- support vector
- target word
- technique
- test set
- text
- training
- training data
- transformation
- unlabeled examples
- word
- word corpus
- word sense
- words
