ACL RD-TEC 1.0 Summarization of P06-2122
Paper Title:
INDUCING WORD ALIGNMENTS WITH BILEXICAL SYNCHRONOUS TREES
INDUCING WORD ALIGNMENTS WITH BILEXICAL SYNCHRONOUS TREES
Authors: Hao Zhang and Daniel Gildea
Primarily assigned technology terms:
- algorithm
- automatic system
- bilexical parsing
- bilingual alignment
- bootstrap
- c + +
- capitalization
- chart parser
- chart parsing
- chart parsing algorithm
- computational linguistics
- computing
- cyk-style chart parsing
- decoding
- dp algorithm
- dynamic programming
- em training
- expectation maximization
- head selection
- inferencing
- inside-outside algorithm
- inside-outside parsing
- itg parse
- itg parsing
- lexicalization
- machine translation
- modeling
- mt systems
- parser
- parsers
- parsing
- parsing algorithm
- probabilistic parser
- programming framework
- pruning
- scoring
- smoothing
- splitting
- statistical machine translation
- synchronous parsing
- syntactic reordering
- tic-tac-toe pruning
- training algorithm
- transduction
- unsupervised training
- viterbi
- viterbi inference
- witten-bell smoothing
- word alignment
Other assigned terms:
- alignment error rate
- alignment task
- association for computational linguistics
- beam
- bilingual corpus
- bitext
- bitext space
- cache
- case
- chinese words
- chinese-english newswire text
- computational complexity
- context free grammars
- corpora
- data set
- dependency model
- dependency structure
- dependency structures
- dependency tree
- derivation
- development set
- distribution
- english sentence
- english vocabulary
- error rate
- estimation
- evaluations
- fact
- foreign language
- foreign words
- formalisms
- french
- generative model
- gold standard
- grammar
- grammar formalisms
- grammars
- head word
- ibm model
- ibm models
- input string
- inversion transduction grammar
- language pair
- language pairs
- large corpora
- lexical information
- lexical rules
- linguistic
- linguistics
- local maxima
- meaning
- measures
- nonterminal
- nonterminals
- pairs of words
- parallel corpus
- parameter space
- parse
- parse tree
- parser output
- pcfg
- precision
- probabilistic model
- probabilities
- probability
- production rules
- pronouns
- reordering
- sentence
- sentence pair
- sentences
- source language
- subtree
- symbol
- symbols
- target language
- target language string
- target string
- technique
- terms
- test data
- test data set
- test set
- text
- time complexity
- tokens
- training
- training corpus
- training data
- transduction grammar
- translation model
- translation pair
- translation probabilities
- translations
- tree
- tree structure
- trees
- uniform distribution
- verb
- viterbi parse
- vocabulary
- word
- word alignments
- word level
- word level alignment
- word pair
- words
