ACL RD-TEC 1.0 Summarization of N06-1001

Paper Title:
CAPITALIZING MACHINE TRANSLATION

Authors: Wei Wang and Kevin Knight and Daniel Marcu

Other assigned terms:

  • alignment information
  • ambiguity
  • approach
  • bilingual corpus
  • bitext
  • bleu
  • bleu scores
  • case
  • case information
  • chunks
  • corpora
  • corpus size
  • data sets
  • derivation
  • development set
  • distribution
  • entropy
  • entropy markov model
  • error rate
  • estimation
  • experimental results
  • fact
  • feature
  • feature value
  • feature weight
  • feature weights
  • frame
  • french
  • gaussian prior
  • heuristic
  • heuristics
  • knowledge
  • labeling
  • language information
  • language model
  • language models
  • language pair
  • language pairs
  • large training
  • lexical ambiguity
  • log-likelihood
  • machine translation output
  • monolingual capitalization model
  • n-gram
  • names
  • performance comparison
  • phrase
  • precision
  • probabilistic model
  • probabilities
  • probability
  • process
  • punctuation
  • punctuation mark
  • punctuation marks
  • resolution problem
  • right-hand side
  • sentence
  • sentence pair
  • sentences
  • source language
  • source sentence
  • surface form
  • tag sequence
  • tags
  • target language
  • target language model
  • target sentence
  • target vocabulary
  • technology
  • term
  • terms
  • text
  • training
  • training corpus
  • training data
  • training set
  • translation model
  • translation models
  • translation output
  • translation probability
  • translation rule
  • translation table
  • translations
  • trigram
  • trigram language model
  • vocabulary
  • weight vector
  • word
  • word alignments
  • word pair
  • words

Extracted Section Types:


This page last edited on 10 May 2017.

*** ***