ACL RD-TEC 1.0 Summarization of W06-1654

Paper Title:
RANDOM INDEXING USING STATISTICAL WEIGHT FUNCTIONS

Authors: James Gorman and James R. Curran

Other assigned terms:

  • acquisition task
  • approach
  • association for computational linguistics
  • beam
  • bilingual corpora
  • bilingual lexicon
  • bilingual lexicons
  • british national corpus
  • co-occurrence
  • co-occurrence matrix
  • concreteness
  • context information
  • context vector
  • context vectors
  • corpora
  • corpus size
  • cosine measure
  • data set
  • data sets
  • dice
  • dictionary
  • dimensionality
  • distance measure
  • distribution
  • distributional similarity
  • document
  • europarl corpora
  • evaluation data
  • evaluation measures
  • foreign language
  • frequency cut-off
  • frequency distribution
  • gold standard
  • grammatical relation
  • grammatical relations
  • index
  • large corpus
  • latent semantic
  • lemma
  • lexical resources
  • lexicon
  • linguistics
  • mapping
  • meaning
  • meanings
  • measure
  • measures
  • method
  • multi-word expression
  • natural language
  • nouns
  • paragraph
  • paragraphs
  • precision
  • probability
  • projection
  • relation
  • semantic
  • semantic similarity
  • sentence
  • similarity scores
  • size of the corpus
  • source language
  • suffix
  • synonym
  • synonyms
  • synonymy
  • target language
  • target languages
  • technique
  • term
  • terms
  • text
  • thesaurus
  • token frequency
  • training
  • translation candidate
  • translations
  • vector space
  • vocabulary
  • vocabulary size
  • weighting scheme
  • window-based context
  • word
  • word corpus
  • wordnet
  • words

Extracted Section Types:


This page last edited on 10 May 2017.

*** ***