ACL RD-TEC 1.0 Summarization of J93-2006

Paper Title:
COPING WITH AMBIGUITY AND UNKNOWN WORDS THROUGH PROBABILISTIC MODELS

Authors: Ralph Weischedel and Richard Schwartz and Jeff Palmucci and Marie Meteer and Lance Ramshaw

Other assigned terms:

  • ambiguity
  • ambiguous words
  • annotated corpora
  • approach
  • association for computational linguistics
  • capitalization information
  • case
  • case frame
  • case frame information
  • conditional probabilities
  • conditional probability
  • context-free rule
  • corpora
  • database query
  • dialogues
  • dictionaries
  • dictionary
  • domain knowledge
  • domain-independent knowledge
  • domain-specific knowledge
  • error rate
  • estimation
  • events
  • fact
  • feature
  • formalism
  • frame
  • grammar
  • handcrafted knowledge
  • head noun
  • heuristics
  • histogram
  • hypotheses
  • hypothesis
  • independence assumption
  • input string
  • intention
  • interpretation
  • interpreter
  • knowledge
  • labeling
  • language database
  • language model
  • language models
  • large corpora
  • lexical features
  • lexical information
  • lexical level
  • lexical semantics
  • likelihood
  • linguistic
  • linguistics
  • local context
  • markov independence
  • markov models
  • meaning
  • measure
  • message
  • message understanding conference
  • method
  • muc-3
  • n-gram
  • n-gram model
  • natural language
  • natural language database
  • noun category
  • noun phrase
  • nouns
  • ordered list
  • parse
  • parse tree
  • part of speech
  • part-of-speech
  • partial parses
  • parts of speech
  • past participle
  • penn treebank
  • penn treebank project
  • pennsylvania treebank
  • phrase
  • phrase attachment
  • plural noun
  • portability
  • predictive power
  • preposition
  • prepositional phrase
  • prepositional phrase attachment
  • prepositional phrases
  • preprocessor
  • priori
  • probabilistic language model
  • probabilistic model
  • probabilistic models
  • probabilities
  • probability
  • probability model
  • probability theory
  • procedure
  • process
  • processing time
  • proper noun
  • proper noun category
  • punctuation
  • punctuation mark
  • queries
  • query
  • relation
  • right-hand side
  • semantic
  • semantic case
  • semantic class
  • semantic constraints
  • semantic features
  • semantic information
  • semantic interpretation
  • semantic knowledge
  • semantic relation
  • semantic relations
  • semantic representation
  • semantic structure
  • sentence
  • sentences
  • set size
  • speech research
  • statistical models
  • structural ambiguity
  • subcategorization frames
  • subcategorization information
  • supervised mode
  • syntactic and semantic information
  • syntactic knowledge
  • syntactic structure
  • syntax
  • syntax and semantics
  • system performance
  • tag sequence
  • tag set
  • tagged corpus
  • tagging model
  • tags
  • technologies
  • technology
  • terms
  • test set
  • text
  • theory
  • tokens
  • topics
  • training
  • training corpus
  • training data
  • training set
  • training set size
  • transcriptions
  • tree
  • treebank
  • treebank corpus
  • treebank project
  • trees
  • understanding
  • unification formalism
  • unification grammar
  • utterance
  • verb
  • verb sense
  • vocabulary
  • vocabulary size
  • word
  • word features
  • word level
  • word sense
  • word senses
  • word sequence
  • words
  • wsj corpus

Extracted Section Types:


This page last edited on 10 May 2017.

*** ***