ACL RD-TEC 1.0 Summarization of P95-1031

Paper Title:
BAYESIAN GRAMMAR INDUCTION FOR LANGUAGE MODELING

Other assigned terms:

  • bayesian framework
  • bayesian grammar
  • benchmark
  • case
  • chomsky normal form
  • collocational information
  • context-free grammar
  • context-free grammars
  • context-free languages
  • convergence
  • data sets
  • data sparsity
  • dimensionality
  • distribution
  • english text
  • entropy
  • fact
  • formalism
  • grammar
  • grammar formalism
  • grammar rule
  • grammars
  • grammatical structure
  • handwriting
  • heuristic
  • heuristics
  • hypothesis
  • implementation
  • knowledge
  • language model
  • language models
  • large training
  • likelihood
  • linear combination
  • long-distance dependencies
  • mapping
  • measure
  • method
  • methodology
  • minimum description length
  • n-gram
  • n-gram model
  • n-gram models
  • natural language
  • nonterminal
  • nonterminals
  • normal form
  • parameter settings
  • parameter space
  • parameter values
  • parse
  • parsed corpus
  • part-of-speech
  • part-of-speech tag
  • penn treebank
  • posteriori probability
  • prior probability
  • priori
  • probabilistic context-free grammars
  • probabilistic grammar
  • probabilities
  • probability
  • probability distributions
  • procedure
  • process
  • right-hand side
  • search problem
  • search procedure
  • search space
  • search strategy
  • sentence
  • sentences
  • set size
  • symbol
  • symbols
  • tag set
  • term
  • terminals
  • test data
  • text
  • training
  • training and test data
  • training corpus
  • training data
  • training set
  • treebank
  • uniform distribution
  • viterbi parse
  • vocabulary
  • wall street journal text
  • word
  • word sequence
  • words

Extracted Section Types:


This page last edited on 10 May 2017.

*** ***