ACL RD-TEC 1.0 Summarization of W01-0713
Paper Title:
UNSUPERVISED INDUCTION OF STOCHASTIC CONTEXT-FREE GRAMMARS USING DISTRIBUTIONAL CLUSTERING
UNSUPERVISED INDUCTION OF STOCHASTIC CONTEXT-FREE GRAMMARS USING DISTRIBUTIONAL CLUSTERING
Primarily assigned technology terms:
- algorithm
- atis
- bayesian approach
- bracketing
- clustering
- clustering algorithm
- cutoff
- distributional clustering
- dynamic programming
- estimator
- grammar induction
- greedy algorithm
- hierarchical clustering
- induction
- induction algorithm
- inside-outside re-estimation
- learning
- likelihood estimator
- maximum likelihood
- maximum likelihood estimator
- parser
- parsing
- parsing algorithm
- re-estimation
- scoring
- search
- supervised learning
- tagger
- tagging
- tokenisation
- unsupervised algorithm
- unsupervised grammar induction
- unsupervised induction
Other assigned terms:
- abbreviation
- annotation
- annotation scheme
- annotators
- approach
- bracketed corpus
- british national corpus
- cluster
- clusters
- compounding
- computational complexity
- context-free grammars
- correlation
- data set
- distribution
- distributional information
- entropy
- estimation
- fact
- finite verb
- formalism
- gold standard
- grammar
- grammars
- independence assumption
- index
- joint distribution
- likelihood
- linear combination
- markup
- measure
- measures
- minimum description length
- mutual information
- natural language
- non-terminal symbol
- nonterminal
- norm
- noun compounding
- noun phrase
- parse
- parse tree
- part of speech
- part of speech tags
- partial parse
- partial parses
- perplexity
- phrase
- phrase structure
- phrase structure rules
- phrase-structure grammar
- preposition
- probabilities
- probability
- probability distributions
- punctuation
- relation
- semantic
- semantic relationships
- sentence
- sentence boundaries
- sentences
- sparse data
- speech tag
- stochastic context-free grammars
- substring
- suffix
- symbol
- symbols
- syntactic constituents
- syntactic structure
- syntactic variation
- tag set
- tagged text
- tags
- technique
- terminals
- text
- tokens
- tree
- tree structures
- treebank
- verb
- word
- word level
- words
