ACL RD-TEC 1.0 Summarization of W06-3111

Paper Title:
PARTITIONING PARALLEL DOCUMENTS USING BINARY SEGMENTATION

Authors: Jia Xu and Richard Zens and Hermann Ney

Other assigned terms:

  • aligned corpus
  • alignment accuracy
  • alignment model
  • alignment models
  • anchor
  • anchors
  • approach
  • beam
  • bilingual corpora
  • bilingual phrase
  • bilingual sentence
  • bilingual training corpus
  • bleu
  • bleu score
  • break
  • case
  • corpora
  • data consortium
  • distribution
  • document
  • error rate
  • evaluation set
  • experimental results
  • feature
  • hypothesis
  • ibm model
  • interpolation
  • knowledge
  • language model
  • language resources
  • lexicon
  • lexicon entries
  • linguistic
  • linguistic data
  • linguistic data consortium
  • log-linear model
  • mapping
  • measure
  • method
  • model parameters
  • n-gram
  • n-grams
  • nist
  • paragraph
  • paragraphs
  • parallel corpora
  • parallel sentence
  • parallel text
  • phrase
  • probability
  • probability distributions
  • procedure
  • process
  • punctuation
  • punctuation marks
  • recursion
  • reordering
  • search space
  • segmentation accuracy
  • segments
  • sentence
  • sentence pair
  • sentences
  • source language
  • source language sentence
  • source sentence
  • statistics
  • symbol
  • target language
  • target language model
  • target language sentence
  • target sentence
  • text
  • training
  • training corpora
  • training corpus
  • training data
  • training time
  • translation hypothesis
  • translation model
  • translation models
  • translation quality
  • uniform distribution
  • user
  • word
  • word alignment model
  • word alignments
  • word error rate
  • word order
  • words

Extracted Section Types:


This page last edited on 10 May 2017.

*** ***