ACL RD-TEC 1.0 Summarization of W00-1312

Paper Title:
CROSS-LINGUAL INFORMATION RETRIEVAL USING HIDDEN MARKOV MODELS

Authors: Jinxi Xu and Ralph Weischedel

Other assigned terms:

  • ambiguity
  • approach
  • bag of words
  • bilingual dictionaries
  • bilingual dictionary
  • bilingual lexicon
  • bilingual lexicons
  • case
  • characters
  • chinese characters
  • chinese text
  • chinese word
  • chinese words
  • chinese-english lexicon
  • compound words
  • corpora
  • data consortium
  • data set
  • data sets
  • dictionaries
  • dictionary
  • distribution
  • document
  • document frequency
  • empirical results
  • english query
  • english translations
  • estimation
  • evaluation metric
  • fact
  • generation
  • generation process
  • glossary
  • index
  • knowledge
  • large corpus
  • latent semantic
  • lexicon
  • likelihood
  • linguistic
  • linguistic data
  • linguistic data consortium
  • markov models
  • measure
  • method
  • names
  • news corpus
  • non-parallel corpora
  • nouns
  • parallel corpus
  • particle
  • performance ratio
  • person names
  • phrase
  • possible translation
  • precision
  • priori
  • probabilistic model
  • probabilities
  • probability
  • probability estimates
  • probability model
  • process
  • pronunciation
  • queries
  • query
  • query term
  • retrieval model
  • retrieval performance
  • semantic
  • sentences
  • stem
  • stems
  • suffixes
  • symbols
  • synonym
  • synonyms
  • target language
  • technical terms
  • technique
  • term
  • terms
  • test set
  • text
  • topics
  • translation ambiguity
  • translation probabilities
  • translation probability
  • translations
  • uniform distribution
  • vector space
  • word
  • word sense
  • wordnet
  • words

Extracted Section Types:


This page last edited on 10 May 2017.

*** ***