ACL RD-TEC 1.0 Summarization of W00-1306
Paper Title:
SAMPLE SELECTION FOR STATISTICAL GRAMMAR INDUCTION
SAMPLE SELECTION FOR STATISTICAL GRAMMAR INDUCTION
Primarily assigned technology terms:
- algorithm
- binary branching
- bracketing
- categorization
- classification
- classifier
- committee-based sample selection
- committee-based selection
- computing
- databases
- deterministic shift-reduce parser
- disambiguation
- grammar induction
- heuristic search
- induction
- induction algorithm
- induction process
- inside-outside algorithm
- inside-outside re-estimation
- language learning
- language processing
- learner
- learning
- learning algorithm
- learning algorithms
- learning process
- learning system
- mmar induction
- natural language learning
- natural language processing
- parser
- parsers
- parsing
- part-of-speech tagging
- processing
- random selection
- re-estimation
- sample selection
- sampling
- scoring
- search
- selection algorithm
- selection learning
- selective sampling
- semantic parsing
- shift-reduce parser
- supervised training
- syntactic analysis
- tagging
- text categorization
- training process
- tree insertion
- unsupervised induction
- unsupervised learning
- unsupervised learning algorithm
- word-sense disambiguation
Other assigned terms:
- annotated training corpus
- annotation
- annotator
- annotators
- approach
- background knowledge
- binary branching trees
- branching trees
- case
- classification task
- computational complexity
- concept
- context-free grammar
- corpora
- data sparsity
- density function
- distribution
- domain knowledge
- entropy
- estimation
- evaluation function
- formalism
- formalisms
- generation
- grammar
- grammars
- heuristic
- human annotator
- human annotators
- hypothesis
- information theory
- knowledge
- labeled training data
- learning problem
- learning rate
- lexicalized tree
- likelihood
- measure
- measures
- natural language
- parse
- parse tree
- parsing accuracy
- part-of-speech
- part-of-speech tags
- prepositional-phrase attachment
- probabilities
- probability
- probability distribution
- process
- processing time
- semantic
- semantic knowledge
- semantic representation
- sentence
- sentences
- size of the corpus
- statistical grammar
- statistical significance
- stochastic context-free grammar
- stochastic grammar
- structure of a sentence
- structure of the sentence
- syntactic parse
- tags
- technique
- term
- terms
- test data
- text
- theory
- training
- training corpora
- training corpus
- training data
- training examples
- training set
- tree
- tree insertion grammar
- tree structure
- treebank
- trees
- uniform distribution
- vocabulary
- vocabulary size
- words
- wsj corpus
