ACL RD-TEC 1.0 Summarization of W04-2409
Paper Title:
A COMPARISON OF MANUAL AND AUTOMATIC CONSTRUCTIONS OF CATEGORY HIERARCHY FOR CLASSIFYING LARGE CORPORA
A COMPARISON OF MANUAL AND AUTOMATIC CONSTRUCTIONS OF CATEGORY HIERARCHY FOR CLASSIFYING LARGE CORPORA
Authors: Fumiyo Fukumoto and Yoshimi Suzuki
Primarily assigned technology terms:
- algorithm
- approximation
- automatic construction
- bayes classifier
- bayesian clustering
- categorisation
- classification
- classifier
- classifiers
- cluster analysis
- clustering
- clustering algorithm
- clustering method
- clustering technique
- document representation
- error reduction
- learner
- learning
- learning task
- learning techniques
- loss function
- machine learning
- machine learning techniques
- naive bayes
- naive bayes classifier
- neural net
- nlp
- part-of-speech tagger
- partitioning
- probabilistic clustering
- random sampling
- sampling
- searching
- statistical techniques
- tagger
- text categorisation
- text classification
Other assigned terms:
- approach
- category hierarchy
- class distribution
- classification accuracy
- classification performance
- classification problem
- cluster
- clusters
- conditional distribution
- corpora
- data sets
- dictionary
- dictionary data
- distribution
- document
- document set
- entropy
- error rate
- euclidean space
- evaluation methodology
- f measure
- f score
- f-score
- feature
- hierarchical model
- hierarchical representation
- hierarchical structure
- human intervention
- information measure
- large corpora
- large training
- leaf
- learning problem
- measure
- measures
- method
- methodology
- mutual information
- part-of-speech
- posterior
- posterior probability
- precision
- probabilistic approach
- probabilistic model
- probabilities
- probability
- procedure
- process
- representations
- reuters corpus
- seed
- statistics
- technique
- test data
- test set
- text
- training
- training and test data
- training data
- training documents
- training samples
- training set
- tree
- unlabeled examples
- vocabulary
- web content
- web pages
- word
- words
