ACL RD-TEC 1.0 Summarization of P05-1068

Paper Title:
CONTEXT-DEPENDENT SMT MODEL USING BILINGUAL VERB-NOUN COLLOCATION

Authors: Young-Sook Hwang and Yutaka Sasaki

Other assigned terms:

  • aligned corpus
  • ambiguity
  • approach
  • back-off model
  • beam
  • beam size
  • bilingual corpora
  • bilingual correspondence
  • bleu
  • bleu score
  • btec corpus
  • bunsetsu
  • case
  • chunk
  • chunk-based statistical machine translation model
  • chunks
  • collocation
  • computational complexity
  • concept
  • conditional probability
  • content words
  • context information
  • contextual information
  • corpora
  • data sparseness
  • data sparseness problem
  • dependency parse
  • dependency relations
  • dependency relationship
  • dependency tree
  • dependency trees
  • distortion probability
  • distribution
  • edit distance
  • error rate
  • estimation
  • evaluations
  • experimental results
  • fact
  • generation
  • grammatical role
  • heuristics
  • hypotheses
  • hypothesis
  • ibm models
  • idiomatic expressions
  • index
  • japanese sentences
  • joint probability
  • joint probability model
  • knowledge
  • language model
  • language model score
  • language pair
  • linguistic
  • linguistic knowledge
  • local context
  • log-linear model
  • machine translation model
  • markov chain
  • meaning
  • method
  • morpheme
  • morpheme level
  • multi-reference word
  • n-gram
  • nist
  • nouns
  • parse
  • part-of-speech
  • performance evaluation
  • phrase
  • possible translation
  • precision
  • probabilities
  • probability
  • probability distribution
  • probability model
  • processing time
  • reference translations
  • relation
  • reordering
  • search problem
  • search space
  • segments
  • sentence
  • sentences
  • source language
  • source language sentence
  • source sentence
  • sparseness problem
  • tags
  • target language
  • target language model
  • target language sentence
  • target sentence
  • target vocabulary
  • target word
  • test set
  • toolkit
  • training
  • translation candidates
  • translation model
  • translation models
  • translation pair
  • translation probabilities
  • translation probability
  • translations
  • travel expression corpus
  • tree
  • trees
  • verb
  • vocabulary
  • word
  • word error rate
  • word formation
  • word level
  • word order
  • word sequence
  • word-aligned corpus
  • word-based translation model
  • words

Extracted Section Types:


This page last edited on 10 May 2017.

*** ***