ACL RD-TEC 1.0 Summarization of W03-1108

Paper Title:
LEARNING BILINGUAL TRANSLATIONS FROM COMPARABLE CORPORA TO CROSS-LANGUAGE INFORMATION RETRIEVAL: HYBRID STATISTICS-BASED AND LINGUISTICS-BASED APPROACH

Authors: Fatiha Sadat and Masatoshi Yoshikawa and Shunsuke Uemura

Other assigned terms:

  • alphabet
  • approach
  • bilingual dictionaries
  • bilingual dictionary
  • bilingual lexicon
  • bilingual lexicons
  • case
  • characters
  • collocation
  • comparable corpora
  • compounds
  • concept
  • concepts
  • content words
  • context vectors
  • corpora
  • culture
  • dictionaries
  • dictionary
  • document
  • document frequency
  • english translation
  • english translations
  • english verbs
  • evaluations
  • feature
  • foreign words
  • inverse document frequency
  • inverted document frequency
  • katakana
  • knowledge
  • language corpus
  • language pair
  • language pairs
  • large corpora
  • large text corpora
  • lexical resources
  • lexicon
  • linguistic
  • linguistic knowledge
  • linguistic resources
  • linguistics
  • log-likelihood
  • log-likelihood ratio
  • measure
  • method
  • morphological knowledge
  • names
  • natural language
  • nouns
  • parallel corpora
  • part-of-speech
  • phonetic alphabet
  • precision
  • procedure
  • pronunciation
  • queries
  • query
  • query vector
  • retrieval performance
  • seed
  • source language
  • tags
  • target language
  • target language corpus
  • target languages
  • technical terms
  • technique
  • technology
  • term
  • term frequency
  • terms
  • test collection
  • text
  • text corpora
  • topics
  • translation candidates
  • translation model
  • translation models
  • translations
  • two-stages model
  • two-stages translation model
  • vector space
  • vocabulary
  • web pages
  • weighting scheme
  • word
  • word frequencies
  • words

Extracted Section Types:


This page last edited on 10 May 2017.

*** ***