ACL RD-TEC 1.0 Summarization of J05-4003

Paper Title:
IMPROVING MACHINE TRANSLATION PERFORMANCE BY EXPLOITING NON-PARALLEL CORPORA

Primarily assigned technology terms:

Other assigned terms:

  • alignment model
  • alignment template
  • annotation
  • annotation projection
  • approach
  • association for computational linguistics
  • bilingual dictionary
  • bleu
  • bleu scores
  • case
  • chinese-english corpus
  • classification problem
  • cluster
  • comparable corpora
  • comparable corpus
  • content words
  • contextual information
  • corpora
  • corpus size
  • cosine similarity
  • data consortium
  • data sets
  • dictionaries
  • dictionary
  • dictionary coverage
  • dictionary entries
  • discourse
  • document
  • english language
  • english non-parallel newspaper corpora
  • english sentence
  • english translation
  • entropy
  • evaluation metric
  • evaluations
  • extraction process
  • f-score
  • feature
  • feature weights
  • foreign language
  • foreign word
  • french
  • generative model
  • heuristic
  • heuristics
  • ibm model
  • implementation
  • index
  • language model
  • language models
  • language pair
  • language pairs
  • lexicon
  • likelihood
  • linear combination
  • linguistic
  • linguistic data
  • linguistic data consortium
  • linguistics
  • machine translation performance
  • meanings
  • measure
  • method
  • monolingual corpora
  • mt evaluation
  • n-grams
  • names
  • nist
  • nlp applications
  • noise
  • non-parallel corpora
  • non-parallel corpus
  • normalization factor
  • out-of-domain corpus
  • pair similarity
  • paragraph
  • parallel corpora
  • parallel corpus
  • parallel sentence
  • parallel texts
  • parallelism
  • parameter values
  • performance evaluation
  • phrase
  • political discourse
  • precision
  • probabilities
  • probability
  • procedure
  • process
  • processing time
  • programming approach
  • projection
  • query
  • reference translations
  • sentence
  • sentence length model
  • sentence level
  • sentence pair
  • sentence similarity
  • sentences
  • similarity measure
  • similarity score
  • size of the corpus
  • statistics
  • substring
  • test corpora
  • test corpus
  • test data
  • test set
  • tokens
  • toolkit
  • training
  • training and test data
  • training corpora
  • training corpus
  • training data
  • training examples
  • training set
  • translation direction
  • translation equivalents
  • translation model
  • translation pairs
  • translation probabilities
  • translations
  • unigram
  • web pages
  • web site
  • word
  • word alignment model
  • word alignments
  • word order
  • word sense
  • words

Extracted Section Types:


This page last edited on 10 May 2017.

*** ***