ACL RD-TEC 1.0 Summarization of W06-1601
Paper Title:
UNSUPERVISED DISCOVERY OF A STATISTICAL VERB LEXICON
UNSUPERVISED DISCOVERY OF A STATISTICAL VERB LEXICON
Authors: Trond Grenager and Christopher D. Manning
Primarily assigned technology terms:
- add-one smoothing
- algorithm
- argument realization
- bayesian smoothing
- classification
- classifiers
- clustering
- collapsing
- computational linguistics
- em algorithm
- encoding
- expectation-maximization
- factorization
- frame acquisition
- greedy search
- hill-climbing
- human language
- human language acquisition
- identification
- language acquisition
- language processing
- language understanding
- language understanding system
- learning
- learning algorithm
- learning algorithms
- learning method
- learning task
- linking
- modeling
- natural language processing
- natural language understanding
- natural language understanding system
- optimization
- parser
- parsing
- part-of-speech tagger
- processing
- recognition
- rule-based system
- sampling
- search
- semantic role labeling
- smoothing
- smoothing technique
- stanford parser
- subcategorization
- subcategorization frame acquisition
- supervised classification
- syntactic realization
- tagger
- tokenizer
- training method
- unsupervised approach
- unsupervised learning
- unsupervised training
Other assigned terms:
- adjunct
- ambiguity
- annotation
- annotator
- approach
- argument structure
- association for computational linguistics
- bayesian model
- case
- classification task
- cluster
- clusters
- conditional probability
- conditional probability distribution
- corpora
- correlation
- data log likelihood
- data sets
- data sparsity
- derivation
- derivation process
- development set
- dirichlet distribution
- distribution
- fact
- frame
- framenet
- frequency counts
- genre
- geometric distribution
- gold standard
- grammar
- grammatical relations
- graphical representation
- hand-tagged corpora
- head word
- human annotator
- human knowledge
- identification task
- implementation
- joint distribution
- joint probability
- joint probability distribution
- knowledge
- labeling
- language processing tasks
- large corpus
- large training
- learning problem
- lemma
- lexical resource
- lexicon
- likelihood
- likelihood function
- linguist
- linguistic
- linguistic structure
- linguistics
- linguists
- local maxima
- local maximum
- mapping
- mappings
- measure
- measures
- method
- model parameters
- model structure
- names
- natural language
- noise
- noun phrase
- optimization problem
- oracle
- parameter settings
- parameter space
- parse
- parse tree
- part of speech
- part-of-speech
- pause
- penn treebank
- phrase
- precision
- preposition
- prior distribution
- priori
- probabilistic model
- probabilities
- probability
- probability distribution
- procedure
- process
- processing tasks
- propbank
- ptb
- relation
- relative frequency
- role labeling
- search procedure
- semantic
- semantic role
- semantic roles
- sentence
- sentences
- speech information
- statistical model
- statistics
- stem
- stems
- subcategorization frame
- syntactic behavior
- syntactic information
- syntactic parse
- syntactic relation
- syntactic relations
- syntactic relationship
- syntactic representation
- syntactic structure
- syntax
- tags
- target verb
- taxonomy
- technique
- term
- terms
- test set
- text
- theory
- training
- training corpus
- training data
- training set
- training time
- tree
- treebank
- trees
- unannotated text
- understanding
- universal grammar
- verb
- verb argument
- verb lexicon
- verb phrase
- word
- word classes
- word distribution
- words
- wsj corpus
