ACL RD-TEC 1.0 Summarization of N06-1003

Paper Title:
IMPROVED STATISTICAL MACHINE TRANSLATION USING PARAPHRASES

Authors: Chris Callison-Burch and Philipp Koehn and Miles Osborne

Other assigned terms:

  • adjective
  • alignment models
  • array
  • baseline model
  • bilingual parallel corpora
  • bilingual parallel corpus
  • bleu
  • bleu score
  • bleu scores
  • case
  • compounds
  • corpora
  • data sparsity
  • data structure
  • development set
  • dutch
  • english translations
  • error rate
  • estimation
  • europarl corpus
  • evaluation method
  • evaluation methodology
  • evaluation metrics
  • fact
  • feature
  • foreign language
  • foreign word
  • french
  • generation
  • gold standard
  • knowledge
  • language model
  • language model probability
  • language pairs
  • language processing tasks
  • large training
  • large training corpora
  • lexical translation
  • likelihood
  • linguistic
  • linguistic information
  • meaning
  • meanings
  • measure
  • method
  • methodology
  • model parameters
  • model probability
  • mt evaluation
  • n-grams
  • names
  • natural language
  • natural language processing tasks
  • parallel corpora
  • parallel corpus
  • paraphrase
  • paraphrases
  • phrase
  • probabilistic framework
  • probabilities
  • probability
  • process
  • processing tasks
  • reference translation
  • reference translations
  • run-time
  • sentence
  • sentences
  • source language
  • source sentence
  • spanish-english training corpora
  • sparse data
  • statistical natural language
  • suffix
  • target language
  • terms
  • test corpora
  • test set
  • text
  • tokens
  • training
  • training corpora
  • training corpus
  • training data
  • training set
  • training text
  • translation model
  • translation models
  • translation probabilities
  • translation probability
  • translation quality
  • translations
  • vocabulary
  • word
  • word alignments
  • words

Extracted Section Types:


This page last edited on 10 May 2017.

*** ***