ACL RD-TEC 1.0 Summarization of W98-1105
Paper Title:
SEMANTIC TAGGING USING A PROBABILISTIC CONTEXT FREE GRAMMAR
SEMANTIC TAGGING USING A PROBABILISTIC CONTEXT FREE GRAMMAR
Authors: Michael Collins and Scott Miller
Primarily assigned technology terms:
- algorithm
- analyzer
- approximation
- automaton
- bigram tagging
- binary branching
- circus parser
- cky algorithm
- cross-validation
- decoding
- decomposition
- disambiguation
- encoding
- error analysis
- extraction systems
- finite state
- finite state approach
- finite-state automaton
- finite-state tagging
- finite-state transducers
- identification
- information extraction
- information extraction systems
- information extraction tasks
- language modeling
- learning
- learning algorithm
- learning approaches
- learning task
- likelihood estimate
- machine learning
- machine learning approaches
- matching
- maximum likelihood
- modeling
- morphological analyser
- morphological analyzer
- name finding
- named-entity identification
- parameterization
- parser
- part of speech tagging
- part-of-speech tagger
- partial match
- pattern matching
- pos tagger
- pos tagging
- processing
- recognition
- relational learning
- semantic tagging
- shallow syntactic analysis
- smoothing
- smoothing techniques
- speech recognition
- speech recognition m
- speech tagging
- splitting
- stochastic process
- syntactic analysis
- syntactic parser
- tagger
- tagging
- transducers
- word-sense disambiguation
Other assigned terms:
- analyser
- annotation
- annotation effort
- annotator
- approach
- bigram
- bigram model
- case
- cf rule
- chunk
- concept
- conditional probability
- context free grammar
- context free rule
- context-free grammar
- data set
- derivation
- distribution
- events
- extraction problem
- extraction process
- f-measure
- fact
- generative model
- gold standard
- grammar
- head-word
- implementation
- information extraction task
- input text
- joint probability
- knowledge
- labeling
- leaf
- lexical items
- lexicon
- lexieal information
- likelihood
- linguistic
- linguistic pattern
- mapping
- maps
- markov independence
- maximum likelihood estimate
- message
- method
- named-entity
- names
- noise
- nonterminals
- nouns
- part of speech
- part-of-speech
- part-of-speech information
- part-of-speech tags
- parts of speech
- pcfg
- pcfg model
- personal pronoun
- precision
- preposition
- prepositions
- prior probability
- probabilistic approach
- probabilistic model
- probabilities
- probability
- probability distribution
- probability estimates
- process
- pronoun
- pronouns
- proper name
- proper names
- relation
- relative clauses
- semantic
- semantic classes
- semantic roles
- semantic type
- sentence
- sentence level
- sentences
- slot
- sparse data
- statistical framework
- statistical model
- stem
- stems
- stochastic model
- stress
- substring
- syntactic information
- syntactic structure
- syntax
- tagging model
- tagging task
- tags
- terms
- test data
- test set
- text
- topology
- training
- training and test data
- training data
- training example
- training examples
- training set
- tree
- tree structure
- tree structures
- trees
- verb
- verb groups
- word
- word string
- word strings
- words
- world knowledge
