ACL RD-TEC 1.0 Summarization of J01-2004

Paper Title:
PROBABILISTIC TOP-DOWN PARSING AND LANGUAGE MODELING

Other assigned terms:

  • acoustic model
  • ambiguity
  • annotation
  • approach
  • beam
  • beam factor
  • bigram
  • case
  • coefficient
  • community
  • complete parse
  • computational linguists
  • conditional probabilities
  • conditional probability
  • conditional probability model
  • conditional word
  • context-free grammars
  • contextual information
  • convergence
  • corpora
  • cross entropy
  • derivation
  • derivations
  • determiner
  • development set
  • distribution
  • empirical results
  • empty categories
  • entropy
  • error rate
  • estimation
  • events
  • fact
  • feature
  • garden path
  • governing category
  • grammar
  • grammars
  • heuristic
  • heuristics
  • hypotheses
  • input string
  • interpolation
  • interpolation coefficients
  • joint probability
  • language model
  • language model score
  • language models
  • lattice
  • lattices
  • lexical head
  • lexical information
  • lexical items
  • likelihood
  • linear order
  • linguistics
  • linguists
  • long-distance dependencies
  • look-ahead probability
  • meaning
  • measure
  • measures
  • method
  • model perplexity
  • n-gram
  • n-grams
  • natural language
  • noisy input
  • nonterminal
  • nonterminals
  • noun phrase
  • oracle
  • parallelism
  • parse
  • parse tree
  • parser performance
  • parser state
  • parsing accuracy
  • parsing approach
  • parsing model
  • part-of-speech
  • partial parse
  • partial parse tree
  • pcfg
  • pcfgs
  • penn treebank
  • perplexity
  • perplexity measure
  • perplexity reduction
  • phrase
  • precision
  • preposition
  • probabilistic context-free grammars
  • probabilistic grammar
  • probabilistic model
  • probabilities
  • probability
  • probability distribution
  • probability distributions
  • probability estimate
  • probability estimates
  • probability model
  • procedure
  • punctuation
  • recognition errors
  • recognition task
  • relation
  • relative frequency
  • right-hand side
  • running time
  • sbar
  • sentence
  • sentences
  • sparse data
  • speech recognition task
  • statistics
  • structural information
  • structured language model
  • symbol
  • symbols
  • syntactic information
  • syntactic structure
  • tags
  • terms
  • test corpus
  • test data
  • testing corpora
  • text
  • theorem
  • training
  • training corpus
  • training data
  • tree
  • tree representation
  • tree structure
  • treebank
  • trees
  • trigram
  • trigram model
  • underspecification
  • unigram
  • utterance
  • verb
  • verb phrase
  • vocabulary
  • word
  • word error rate
  • word error rates
  • word-by-word basis
  • words

Extracted Section Types:


This page last edited on 10 May 2017.

*** ***