ACL RD-TEC 1.0 Summarization of N03-1033
Paper Title:
FEATURE-RICH PART-OF-SPEECH TAGGING WITH A CYCLIC DEPENDENCY NETWORK
FEATURE-RICH PART-OF-SPEECH TAGGING WITH A CYCLIC DEPENDENCY NETWORK
Authors: Kristina Toutanova and Dan Klein and Christopher D. Manning and Yoram Singer
Primarily assigned technology terms:
- algorithm
- capitalization
- categorization
- classifier
- classifier combination
- claws tagger
- conditional likelihood
- conditional random fields
- crfs
- cutoff
- decision trees
- entity recognizer
- error analysis
- error reduction
- estimation method
- extraction system
- factorization
- gibbs sampling
- graphical model
- hmms
- information extraction
- information extraction system
- learning
- lexicalization
- likelihood estimation
- likelihood estimation method
- linguistic processing
- linking
- logistic regression
- loglinear
- machine learning
- markov model
- maxent
- maximum entropy
- maximum entropy model
- maximum likelihood
- maximum likelihood estimation
- modeling
- named entity recognizer
- network representation
- nlp
- noun tagging
- optimization
- parser
- parsers
- parsing
- part-of-speech tagger
- part-of-speech tagging
- perceptron
- processing
- processor
- question answering
- reasoning
- recognizer
- regression
- regularization
- reporting
- sampling
- scoring
- sentence interpretation
- smoothing
- spelling
- statistical parsers
- statistical parsing
- tagger
- taggers
- tagging
- text categorization
- transformation-based learning
- treebank training
- viterbi
- viterbi algorithm
- voted perceptron
- word modeling
Other assigned terms:
- advanced question answering
- annotator
- approach
- baseline model
- bias
- bidirectional dependency network
- bidirectional model
- binomial model
- case
- conditional markov model
- conditional model
- conditional probabilities
- conditional probability
- conditional probability model
- convergence
- data set
- development set
- disk
- distribution
- entropy
- entropy models
- estimation
- fact
- feature
- feature sets
- feature weights
- gaussian prior
- hmm model
- index
- intelligence
- interpretation
- joint probability
- lexical features
- lexical information
- likelihood
- linguistic
- log-likelihood
- log-linear models
- loglinear model
- markov window
- maxent model
- maximum entropy models
- measure
- method
- modal verb
- n-gram
- named entity
- noise
- nouns
- parse
- parsing models
- part of speech
- part-of-speech
- penn treebank
- polynomial time
- prefixes and suffixes
- preprocessor
- prior distribution
- probabilistic models
- probabilities
- probability
- probability estimate
- probability model
- procedure
- proper noun
- ptb
- research and development
- sentence
- sentences
- sequence model
- set size
- speech tag
- suffix
- suffixes
- symbols
- system performance
- tag sequence
- tag set
- tagging model
- tagging performance
- tagging problem
- tags
- term
- test set
- text
- tokens
- training
- training data
- training examples
- training set
- training set size
- transformation
- treebank
- trees
- unknown word model
- verb
- word
- word features
- word model
- word sequences
- words
