ACL RD-TEC 1.0 Summarization of P04-1060
Paper Title:
EXPERIMENTS IN PARALLEL-TEXT BASED GRAMMAR INDUCTION
EXPERIMENTS IN PARALLEL-TEXT BASED GRAMMAR INDUCTION
Primarily assigned technology terms:
- algorithm
- analysis tool
- bootstrap
- bootstrapping
- bracketing
- classifier
- clustering
- clustering technique
- computing
- dependency parser
- dynamic programming
- dynamic programming algorithm
- em algorithm
- em learning
- em training
- english analysis
- expectation-maximization
- giza
- grammar induction
- grammar induction approach
- identification
- illustration
- induction
- induction process
- information projection
- inside-outside algorithm
- learning
- learning approach
- learning techniques
- machine translation
- parameter reestimation
- parser
- parsers
- parsing
- pcfg induction
- programming algorithm
- reestimation
- right-branching
- shallow analysis
- smoothing
- smoothing techniques
- statistical machine translation
- statistical mt
- statistical word alignment
- structure representation
- supervised grammar induction
- syntactic projection
- taggers
- text classifier
- training algorithm
- training method
- treebank training
- unsupervised technique
- viterbi
- voting
- weighting
- word alignment
- word clustering
Other assigned terms:
- aligned corpus
- aligned parallel corpus
- alignment information
- alignment models
- annotation
- approach
- array
- bayesian framework
- concept
- concepts
- confidence measure
- constituency information
- constituent structure
- constituent\/distituent information
- corpora
- dependency structure
- dependency treebank
- distribution
- english parse
- english sentence
- english syntax
- english text
- europarl corpus
- experimental results
- french
- function words
- gold standard
- grammar
- hypothesis
- ibm models
- implementation
- knowledge
- language pairs
- large training
- learning problem
- likelihood
- linguistic
- manual annotation
- maps
- measure
- measures
- method
- methodology
- noise
- parallel corpora
- parallel corpus
- parallel text
- parallel texts
- paraphrases
- parse
- pcfg
- pcfgs
- penn treebank
- phrase
- phrase structure
- precision
- probability
- process
- projection
- punctuation
- regular expressions
- reordering
- right-branching structure
- scalability
- semi-supervised approach
- sentence
- sentences
- substring
- symbols
- syntactic constituents
- syntax
- target language
- technique
- technology
- test data
- test set
- text
- toolkit
- topology
- training
- training corpus
- training data
- training set
- tree
- tree structure
- treebank
- treebank annotation
- trees
- weighting scheme
- word
- word order
- words
