ACL RD-TEC 1.0 Summarization of W04-3207
Paper Title:
BILINGUAL PARSING WITH FACTORED ESTIMATION: USING ENGLISH TO PARSE KOREAN
BILINGUAL PARSING WITH FACTORED ESTIMATION: USING ENGLISH TO PARSE KOREAN
Authors: David A. Smith and Noah A. Smith
Primarily assigned technology terms:
- algorithm
- analyzer
- approximation
- automaton
- beam search
- bilingual parser
- bilingual parsing
- bracketing
- broadcast information service
- cky parsing
- classification
- coupling
- cross-validation
- dependency parsing
- disambiguation
- discriminative estimation
- discriminative training
- dynamic programming
- english analysis
- english parser
- factored modeling
- feature selection
- finite-state transducers
- giza
- hidden markov
- hidden markov models
- iterative scaling
- korean morphological analysis
- korean parser
- korean parsing
- lemmatization
- lexicalization
- likelihood estimation
- matching
- maximum likelihood
- maximum likelihood estimation
- modeling
- monolingual parsing
- morphological analysis
- morphological analyzer
- morphological disambiguation
- morphological processing
- morphology
- numerical optimization
- optimization
- parameter estimation
- parameterization
- parser
- parser implementation
- parsers
- parsing
- parsing algorithm
- processing
- processing tools
- programming framework
- pruning
- right-branching
- search
- split parsing
- statistical translation
- supervised training
- synchronous parsing
- syntactic analysis
- tagging
- thresholding
- transducers
- transduction
- treetransformation
- uniform-cost search
- unsupervised estimation
- viterbi
- viterbi algorithm
- word alignment
- word matching
- word translation
- word-alignment
- word-to-word translation
Other assigned terms:
- analysis model
- approach
- backoff
- beam
- bigram
- bilingual corpus
- bilingual text
- bitext
- case
- conditional probabilities
- conditional probability
- context-free grammars
- corpora
- correlation
- data sparseness
- dependency graph
- dependency model
- dependency structure
- dictionary
- disambiguation model
- discipline
- english dependency
- english parse
- english sentence
- english syntax
- english translation
- english translations
- estimation
- evaluations
- events
- fact
- feature
- feature weights
- formalism
- gaussian prior
- generation
- generative model
- grammar
- grammars
- head automaton grammar
- head word
- heuristics
- ibm models
- implementation
- independence assumption
- inversion transduction grammar
- knowledge
- korean morphology
- labeled training data
- large corpus
- lattice
- lexical-functional grammar
- likelihood
- log-linear model
- log-linear models
- mapping
- mappings
- markov models
- measure
- measures
- model parameters
- morpheme
- morphemes
- noisy channel
- nonterminal
- nonterminals
- nouns
- parallel corpus
- parallel text
- parse
- parsing accuracy
- parsing models
- pcfg
- pcfgs
- phrase
- pos tag
- precision
- probabilistic context-free grammars
- probabilistic grammar
- probabilities
- probability
- process
- production rule
- projection
- punctuation
- rewrite rules
- run-time
- search space
- semantic
- semantic content
- sentence
- sentences
- set size
- sparse data
- standard deviation
- statistical models
- surface form
- surface form word
- symbols
- syntactic constituent
- syntax
- syntax model
- tag sequence
- tags
- terminals
- terms
- test data
- test set
- text
- tokens
- training
- training and test data
- training corpus
- training data
- training set
- training set size
- transduction grammar
- transformation
- translation model
- translation models
- translations
- tree
- treebank
- trees
- trigram
- trigram model
- unigram
- vocabulary
- vocabulary size
- word
- word alignments
- word frequencies
- word-to-word translation model
- words
- wsj treebank
