ACL RD-TEC 1.0 Summarization of W06-0101

Paper Title:
IMPROVING CONTEXT VECTOR MODELS BY FEATURE CLUSTERING FOR AUTOMATIC THESAURUS CONSTRUCTION

Authors: Jia-Ming You and Keh-Jiann Chen

Other assigned terms:

  • approach
  • association for computational linguistics
  • case
  • chinese language
  • cluster
  • co-occurrence
  • co-occurrence matrix
  • computational feasibility
  • context features
  • context information
  • context vector
  • context vectors
  • context words
  • contextual feature
  • contextual features
  • contextual information
  • contextual word
  • corpora
  • correlation
  • cross entropy
  • data sparseness
  • data sparseness problem
  • distribution
  • entropy
  • evaluation metrics
  • evaluations
  • experimental results
  • fact
  • feature
  • feature vector
  • feature vectors
  • hierarchical structure
  • hownet
  • hypernym
  • hyponym
  • index
  • information content
  • knowledge
  • latent semantic
  • linguistic
  • linguistic resources
  • linguistics
  • mapping
  • meaning
  • meanings
  • measure
  • measures
  • method
  • news corpus
  • nouns
  • part of speech
  • performance evaluation
  • precision
  • probability
  • process
  • proper noun
  • relation
  • semantic
  • semantic classes
  • semantic index
  • semantic roles
  • sentences
  • similarity between words
  • similarity function
  • skew divergence
  • sparseness problem
  • synonym
  • synonym set
  • synonyms
  • syntactic relations
  • taxonomy
  • technique
  • term
  • term frequency
  • testing data
  • text
  • thesaurus
  • tokens
  • verb
  • word
  • word features
  • word information
  • word meaning
  • word meanings
  • word pair
  • word sense
  • word senses
  • wordnet
  • words

Extracted Section Types:


This page last edited on 10 May 2017.

*** ***