ACL RD-TEC 1.0 Summarization of P06-1011

Paper Title:
EXTRACTING PARALLEL SUB-SENTENTIAL FRAGMENTS FROM NON-PARALLEL CORPORA

Authors: Dragos Stefan Munteanu and Daniel Marcu

Other assigned terms:

  • alignment models
  • alignment procedure
  • alignment task
  • alignment template
  • approach
  • association for computational linguistics
  • bilingual corpora
  • bleu
  • bleu score
  • case
  • chunks
  • comparable corpora
  • comparable corpus
  • conditional probability
  • corpora
  • development set
  • distribution
  • document
  • events
  • fact
  • genre
  • heuristic
  • heuristics
  • hypothesis
  • implementation
  • inflected form
  • knowledge
  • language models
  • language pairs
  • lexicon
  • lexicon entry
  • likelihood
  • likelihood-ratio
  • linguistics
  • meaning
  • measure
  • method
  • methodology
  • noise
  • non-parallel corpora
  • pairs of words
  • parallel corpora
  • parallel corpus
  • parallel sentence
  • parallel texts
  • parallel training corpus
  • parallelism
  • phrase
  • precision
  • probabilistic lexicon
  • probabilities
  • probability
  • probability distribution
  • probability distributions
  • procedure
  • punctuation
  • query
  • reference translation
  • reordering
  • segments
  • sentence
  • sentence level
  • sentence pair
  • sentences
  • signal
  • source language
  • source sentence
  • statistic
  • target language
  • target languages
  • target sentence
  • target word
  • test data
  • text
  • tokens
  • training
  • training corpus
  • training data
  • translation candidate
  • translation lexicon
  • translation probabilities
  • translational equivalence
  • translations
  • word
  • word alignment task
  • word association
  • word pair
  • words

Extracted Section Types:


This page last edited on 10 May 2017.

*** ***