ACL RD-TEC 1.0 Summarization of W05-0823

Paper Title:
STATISTICAL MACHINE TRANSLATION OF EUPARL DATA BY USING BILINGUAL N-GRAMS

Authors: Rafael E. Banchs and Josep M. Crego and Adriàde Gispert and Patrik Lambert and José B. Mariño

Other assigned terms:

  • aligned corpus
  • aligned sentence
  • approach
  • beam-search strategy
  • bilingual corpus
  • bilingual sentence
  • bleu
  • bleu scores
  • case
  • corpora
  • data sets
  • data sparseness
  • development set
  • entropy
  • feature
  • french
  • histogram
  • hypothesis
  • ibm model
  • joint probability
  • language model
  • language modeling toolkit
  • language pair
  • language pairs
  • lexicon
  • lexicon model
  • log-linear combination
  • log-linear model
  • method
  • modality
  • model performance
  • modeling toolkit
  • n-gram
  • n-gram model
  • n-grams
  • noisy channel
  • parallel texts
  • phrase-based translation model
  • probabilities
  • probability
  • procedure
  • reordering
  • sentence
  • sentence pair
  • sentences
  • target language
  • target language model
  • target languages
  • target word
  • technology
  • test data
  • test set
  • tokens
  • toolkit
  • training
  • training data
  • training set
  • translation hypothesis
  • translation model
  • translation probabilities
  • translation probability
  • translation quality
  • translations
  • vocabulary
  • vocabulary size
  • word
  • words

Extracted Section Types:


This page last edited on 10 May 2017.

*** ***