ACL RD-TEC 1.0 Summarization of P06-2112

Paper Title:
WORD ALIGNMENT FOR LANGUAGES WITH SCARCE RESOURCES USING BILINGUAL CORPORA OF OTHER LANGUAGE PAIRS

Authors: Haifeng Wang and Hua Wu and Zhanyi Liu

Other assigned terms:

  • alignment error rate
  • alignment model
  • alignment models
  • alignment problem
  • ambiguous words
  • approach
  • association for computational linguistics
  • bilingual corpora
  • bilingual corpus
  • bilingual sentence
  • case
  • chinese sentence
  • chinese word
  • chinese-english corpus
  • context words
  • corpora
  • cross-language word similarity
  • dictionaries
  • dictionary
  • distortion probability
  • distribution
  • english language
  • english sentence
  • english translation
  • error rate
  • estimation
  • evaluation metrics
  • evaluations
  • experimental results
  • f-measure
  • fact
  • feature
  • feature vector
  • feature vectors
  • head word
  • hindi
  • hmm model
  • ibm model
  • ibm models
  • index
  • interpolation
  • interpretation
  • japanese sentences
  • japanese word
  • language pair
  • language pairs
  • length distribution
  • lexicon
  • linguistic
  • linguistics
  • method
  • noise
  • parallel corpora
  • parallel corpus
  • parallel texts
  • precision
  • probabilities
  • probability
  • process
  • relative error reduction
  • sentence
  • sentence pair
  • sentences
  • source sentence
  • statistics
  • target sentence
  • target word
  • testing data
  • thesaurus
  • training
  • training corpora
  • training data
  • translation accuracy
  • translation dictionary
  • translation lexicon
  • translation probabilities
  • translation probability
  • transliteration similarity
  • tree
  • word
  • word alignment model
  • word similarity
  • wordnet
  • words

Extracted Section Types:


This page last edited on 10 May 2017.

*** ***