ACL RD-TEC 1.0 Summarization of A00-2021
Paper Title:
EXPLOITING AUXILIARY DISTRIBUTIONS IN STOCHASTIC UNIFICATION-BASED GRAMMARS
EXPLOITING AUXILIARY DISTRIBUTIONS IN STOCHASTIC UNIFICATION-BASED GRAMMARS
Authors: Mark Johnson and Stefan Riezler
Primarily assigned technology terms:
- 10-fold crossvalidation
- algorithm
- broad-coverage parser
- clustering
- computing
- crossvalidation
- entropy estimation
- estimation procedure
- estimation process
- estimator
- expectation-maximization
- expectation-maximization algorithm
- frequency estimator
- likelihood estimation
- maximum entropy
- maximum likelihood
- maximum likelihood estimation
- maximum pseudo-likelihood estimation
- normalization
- parser
- parsers
- parsing
- pseudo-likelihood estimation
- right-branching
- shallow parser
- smoothing
Other assigned terms:
- adjunct
- annotation
- approach
- attribute-value pair
- british national corpus
- c-structure\/f-structure pair
- categorial grammars
- cluster
- clustering model
- conditional distribution
- conditional probabilities
- conditional probability
- conditional probability distribution
- corpora
- dimensionality
- distribution
- distributional information
- empirical evaluation
- entropy
- estimation
- f-structure
- f-structures
- fact
- feature
- feature set
- feature structure
- feature vector
- formalism
- functional grammar
- grammar
- grammars
- grammatical features
- grammatical function
- grammatical relation
- grammatical role
- hpsgs
- interpretation
- joint distribution
- kullback-leibler divergence
- language models
- large corpora
- lexical features
- lexical functional grammar
- lexical information
- lexical model
- lexical-functional grammar
- likelihood
- linguistic
- linguistic structure
- linguistic structures
- manual annotation
- mapping
- measure
- measures
- method
- normalization factor
- nouns
- parse
- parser performance
- pcfg
- pcfgs
- predicates
- prepositions
- probabilistic model
- probabilities
- probability
- probability distribution
- probability distributions
- procedure
- process
- relation
- relative frequency
- selectional preference
- selectional preference information
- selectional preferences
- semantic
- semantic constraints
- sentence
- sentences
- slot
- sparse data
- statistical model
- statistical models
- stochastic grammar
- subgraph
- suffix
- syntactic structure
- syntactic structures
- system performance
- technique
- term
- test corpus
- test set
- text
- training
- training corpus
- training data
- transformational grammars
- transitive verb
- tree
- trees
- verb
- verbmobil corpus
- word
