ACL RD-TEC 1.0 Summarization of W93-0109
Paper Title:
THE AUTOMATIC ACQUISITION OF FREQUENCIES OF VERB SUBCATEGORIZATION FRAMES FROM TAGGED CORPORA
THE AUTOMATIC ACQUISITION OF FREQUENCIES OF VERB SUBCATEGORIZATION FRAMES FROM TAGGED CORPORA
Authors: Akira Ushioda and David Evans and Ted Gibson and Alex Waibel
Primarily assigned technology terms:
- boundary detection
- computing
- deterministic processing
- frequency estimation
- identification
- loglinear
- maximum likelihood
- noun phrase parsing
- parser
- parsing
- phrase boundary detection
- phrase parsing
- probabilistic parsing
- processing
- regular expression
- smoothing
- statistical analysis
- statistical estimation
- statistical method
- subcategorization
- tile
- tokenization
- verb subcategorization
Other assigned terms:
- adjunct
- adverb
- approach
- automatic processing
- brown corpus
- case
- contingency table
- corpora
- distribution
- error rate
- estimation
- feature
- feature sets
- finite verb
- finite-state grammar
- frame
- frequency distribution
- gold standard
- grammar
- heuristics
- histogram
- implementation
- knowledge
- large corpus
- lexical knowledge
- likelihood
- linguistic
- linguistic phenomena
- loglinear model
- main clause
- measure
- measures
- method
- noun phrase
- noun phrase boundary
- noun phrases
- np government
- penn treebank
- penn treebank project
- penn treebank tagset
- phrase
- phrase boundary
- preposition
- prepositional phrases
- probability
- procedure
- process
- pronoun
- pronouns
- punctuation
- regular expressions
- relative clause
- relative clauses
- relative pronoun
- sentence
- sentences
- statistical approach
- statistics
- structure of a sentence
- subcategorization frame
- subcategorization frames
- syntactic context
- syntactic features
- syntactic structure
- syntactic structures
- tagged corpora
- tagged corpus
- tagged text
- tagset
- target verb
- test corpora
- test corpus
- text
- theorem
- tokens
- training
- training corpus
- training samples
- training text
- treebank
- treebank project
- verb
- verb phrase
- verb-subcat frame
- wall street journal corpus
- words
- wsj corpus
