ACL RD-TEC 1.0 Summarization of P92-1017
Paper Title:
INSIDE-OUTSIDE REESTIMATION FROM PARTIALLY BRACKETED CORPORA
INSIDE-OUTSIDE REESTIMATION FROM PARTIALLY BRACKETED CORPORA
Authors: Fernando Pereira and Yves Schabes
Primarily assigned technology terms:
- algorithm
- atis
- bracketing
- clustering
- constituent analysis
- grammar inference
- grammatical inference
- hidden markov
- hidden markov models
- hmms
- information system
- inside-outside algorithm
- inside-outside reestimation
- language understanding
- linguistic structure inference
- modeling
- parameter estimation
- parameter reestimation
- parser
- recognition
- reestimation
- reestimation algorithm
- self-organizing grammar inference
- speech recognition
- structure inference
- training algorithm
Other assigned terms:
- abbreviation
- annotators
- artificial language
- bracketed corpora
- bracketed corpus
- case
- constituent structure
- context-free grammar
- context-free grammars
- convergence
- corpora
- cross entropy
- data sparseness
- derivation
- derivations
- distribution
- entropy
- estimation
- fact
- finite set
- formalisms
- grammar
- grammar formalisms
- grammar reestimation
- grammars
- grammatical structure
- hierarchical model
- hierarchical structure
- implementation
- language corpus
- language models
- lexicalized tree-adjoining grammars
- likelihood
- linguistic
- linguistic structure
- linguists
- local maxima
- markov models
- meaning
- method
- mutual information
- n-grams
- natural language
- natural-language
- nonterminal
- nonterminals
- noun phrases
- parse
- parse tree
- parsed corpus
- part-of-speech
- part-of-speech tags
- parts of speech
- penn treebank
- probabilities
- probability
- probability estimates
- procedure
- process
- pronoun
- pronouns
- punctuation
- punctuation mark
- relative frequency
- sentence
- sentence structure
- sentences
- sentential form
- spoken language
- spoken language corpus
- statistical models
- statistics
- stochastic context-free grammar
- stochastic context-free grammars
- substring
- symbol
- symbols
- tags
- terminals
- terms
- test data
- test set
- text
- time complexity
- training
- training and test data
- training corpus
- training material
- training set
- training text
- transcriptions
- tree
- tree bank
- tree-adjoining grammars
- treebank
- trees
- understanding
- verb
- words
