ACL RD-TEC 1.0 Summarization of C96-1003
Paper Title:
CLUSTERING WORDS WITH THE MDL PRINCIPLE
CLUSTERING WORDS WITH THE MDL PRINCIPLE
Authors: Hang Li and Naoki Abe
Primarily assigned technology terms:
- algorithm
- annealing algorithm
- automatic construction
- classification
- clustering
- clustering algorithm
- clustering method
- clustering technique
- coding
- computing
- data compression
- disambiguation
- disambiguation method
- encoding
- estimator
- language processing
- language processing system
- learning
- learning method
- likelihood estimator
- maximum likelihood
- maximum likelihood estimator
- natural language processing
- natural language processing system
- noun clustering
- pp-attachment disambiguation
- processing
- qualitative evaluation
- silnulatcd annealing
- silnulated annealing
- simulated annealing
- smoothing
- smoothing method
- smoothing technique
- statistical estimation
- statistical natural language processing
- tile
- word clustering
Other assigned terms:
- case
- case frame
- cluster
- clusters
- co-occurrence
- co-occurrences
- coding scheme
- convergence
- data sparseness
- data sparseness problem
- distribution
- estimation
- experimental results
- frame
- information theory
- joint distribution
- likelihood
- mdl principle
- measure
- method
- minimum description length
- natural language
- nouns
- penn tree bank
- pp-attachment
- probabilistic model
- probabilities
- probability
- probability distribution
- probability model
- process
- similarity measure
- slot
- sparseness problem
- statistical natural language
- statistics
- subjectivity
- technique
- terms
- test data
- theory
- thesaurus
- tile description
- training
- training data
- training data.
- tree
- tree bank
- verb
- word
- word classes
- word co-occurrence
- word-net
- wordnet
- words