ACL RD-TEC 1.0 Summarization of W04-3227
Paper Title:
PHRASE PAIR RESCORING WITH TERM WEIGHTING FOR STATISTICAL MACHINE TRANSLATIO
PHRASE PAIR RESCORING WITH TERM WEIGHTING FOR STATISTICAL MACHINE TRANSLATIO
Authors: Bing Zhao and Stephan Vogel and Matthias Eck and Alex Waibel
Primarily assigned technology terms:
- algorithm
- bilingual bracketing
- bracketing
- context modeling
- cross validation
- decoder
- decoding
- dynamic programming
- dynamic programming search
- geometric interpolation
- hidden markov
- hidden markov model
- information retrieval
- linear interpolation
- local word reordering
- machine translation
- machine translation framework
- machine translation system
- machine translation systems
- markov model
- maximum likelihood
- mining
- modeling
- pair extraction
- phrasal translation
- phrase alignment
- phrase extraction
- phrase translation
- phrase-based machine translation
- phrase-based statistical machine translation
- phrase-based translation
- preprocessing
- reasoning
- regularization
- reranking
- rescoring
- search
- segmentation
- sentence alignment
- smoothing
- statistical machine translation
- statistical machine translation system
- statistical translation
- syntax-based alignment
- term weighting
- transducer
- transducers
- translation system
- translation systems
- validation
- vector representation
- viterbi
- viterbi alignment
- weighting
- word alignment
- word reordering
- word segmentation
- word-reordering
- word-to-word translation
Other assigned terms:
- alignment model
- alignment models
- alignment probability
- ambiguity
- approach
- bag of words
- bilingual corpus
- bilingual dictionaries
- bleu
- bleu metric
- bleu score
- candidate translation
- chinese sentence
- co-occurrence
- comparable corpus
- content words
- cosine distance
- determiners
- dictionaries
- dictionary
- distance metric
- distribution
- document
- document frequency
- document vector
- english corpus
- estimation
- events
- experimental results
- function words
- gaussian distribution
- generative model
- grammar
- hypotheses
- hypothesis
- ibm models
- infinitive form
- information content
- interpolation
- inverse document frequency
- knowledge
- language model
- large corpus
- lattice
- lexicon
- likelihood
- local context
- mappings
- measure
- n-gram
- nist
- noise
- noun phrases
- nouns
- parallel corpus
- parallel sentence
- phrase
- probabilities
- probability
- process
- query
- query vector
- reordering
- representations
- sentence
- sentence pair
- sentences
- similarity function
- source language
- source sentence
- statistical framework
- statistics
- sub-tree
- syntax
- target language
- target languages
- target sentence
- term
- term frequency
- terms
- test data
- text
- tokens
- toolkit
- training
- training corpus
- training data
- translation candidate
- translation candidates
- translation model
- translation models
- translation pair
- translation pairs
- translation probabilities
- translation probability
- translation quality
- translation score
- translation task
- translations
- trigram
- trigram model
- vector space
- viterbi path
- vocabulary
- weight vector
- word
- word alignments
- word co-occurrence
- word sequence
- words
