ACL RD-TEC 1.0 Summarization of P98-1034
Paper Title:
ERROR-DRIVEN PRUNING OF TREEBANK GRAMMARS FOR BASE NOUN PHRASE IDENTIFICATION
ERROR-DRIVEN PRUNING OF TREEBANK GRAMMARS FOR BASE NOUN PHRASE IDENTIFICATION
Authors: Claire Cardie and David Pierce
Primarily assigned technology terms:
- 5-fold cross validation
- algorithm
- analyzer
- bracketing
- corpus-based acquisition
- corpus-based approach
- cross validation
- decision tree
- error-driven pruning
- fine-grained pruning
- finite-state transducers
- grammar induction
- identification
- incremental pruning
- induction
- language processing
- learning
- learning algorithm
- learning algorithms
- learning approach
- lexicalization
- longest matching
- machine learning
- machine learning algorithms
- manufacturing
- matching
- natural language processing
- nlp
- nlp system
- noun phrase identification
- np algorithm
- np identification
- parser
- parsers
- parsing
- part-of-speech tagger
- part-of-speech tagging
- partial parser
- partial parsing
- phrase identification
- post-processing
- processing
- pruning
- pruning strategy
- ranking
- repair
- search
- statistical parser
- tagger
- tagging
- threshold pruning
- thresholding
- transducers
- transformation-based learning
- validation
- weighted finite-state transducers
Other assigned terms:
- adverb
- ambiguity
- annotated corpus
- approach
- base noun
- base noun phrase
- brown corpus
- case
- case frame
- corpora
- data sparseness
- data structure
- frame
- frame representation
- functional structure
- grammar
- grammars
- heuristic
- heuristics
- implementation
- incremental approach
- input text
- intention
- knowledge
- language processing applications
- lexical information
- lexical items
- lexical knowledge
- linguistic
- matching rule
- measure
- method
- natural language
- natural language processing applications
- nlp tasks
- noun phrase
- noun phrase grammar
- noun phrases
- part-of-speech
- part-of-speech information
- part-of-speech tag
- part-of-speech tags
- parts of speech
- penn treebank
- penn treebank ii
- phrase
- precision
- preposition
- probabilistic model
- procedure
- process
- pronouns
- punctuation
- rule set
- rule sets
- semantic
- semantic case
- sentence
- sentences
- stem
- syntactic structure
- tag sequence
- tagged text
- tags
- technique
- terms
- test corpus
- test set
- text
- training
- training corpus
- training data
- training phase
- training time
- tree
- treebank
- verb
- verb groups
- word
- words
- wsj corpus
