ACL RD-TEC 1.0 Summarization of W95-0106
Paper Title:
TRAINABLE COARSE BILINGUAL GRAMMARS FOR PARALLEL TEXT BRACKETING
TRAINABLE COARSE BILINGUAL GRAMMARS FOR PARALLEL TEXT BRACKETING
Primarily assigned technology terms:
- algorithm
- ambiguity resolution
- bilingual language modeling
- bilingual parse
- bracketing
- collocation extraction
- constituent identification
- corpus analysis
- corpus annotation
- data conversion
- decomposition
- em algorithm
- english-chinese translation
- estimation procedure
- expectation-maximization
- identification
- inside-outside algorithm
- language modeling
- learning
- learning procedure
- lexical matching
- machine translation
- matching
- maximum-likelihood
- modeling
- optimization
- parallel corpus analysis
- parallel training
- parameter estimation
- parser
- parsers
- parsing
- parsing algorithm
- rule expansion
- scfg estimation
- sentence alignment
- sentence translation
- sitg parsing
- statistical analysis
- structuring
- tagger
- training algorithm
- training method
- transduction
- unsupervised training
- weighting
- word translation
Other assigned terms:
- abbreviation
- adjective
- ambiguity
- annotation
- approach
- bilingual corpora
- bilingual corpus
- bracketed corpora
- bracketed corpus
- break
- brown corpus
- case
- chinese part-of-speech
- chinese sentence
- chinese word
- chinese words
- collocation
- compositionality
- compounding
- conditional distribution
- context-free grammar
- context-free grammars
- convergence
- corpora
- data set
- derivation
- distribution
- empty string
- english grammar
- english part-of-speech
- english sentence
- estimation
- evaluations
- fact
- formalism
- grammar
- grammars
- grammatical information
- heuristic
- heuristics
- hypothesis
- inversion transduction grammar
- inversion transduction grammars
- knowledge
- lexemes
- lexical translation
- lexicon
- likelihood
- linguistic
- matching process
- method
- model parameter
- nonterminal
- nonterminal category
- nonterminals
- normal form
- nouns
- parallel bilingual corpus
- parallel corpora
- parallel corpus
- parallel text
- parallel training corpus
- parse
- parse tree
- part-of-speech
- penn treebank
- perplexity
- precision
- probabilities
- probability
- procedure
- process
- production rule
- punctuation
- right-hand side
- sentence
- sentence pair
- sentences
- stress
- subtrees
- symbol
- symbols
- syntactic constraints
- syntactic structures
- tagset
- target languages
- terms
- text
- theorem
- tokens
- training
- training corpus
- training data
- training data set
- transduction grammar
- translation accuracy
- translation lexicon
- translation probabilities
- translations
- tree
- treebank
- vocabulary
- word
- word-translation lexicon
- words
