ACL RD-TEC 1.0 Summarization of P97-1024
Paper Title:
INDEPENDENCE ASSUMPTIONS CONSIDERED HARMFUL
INDEPENDENCE ASSUMPTIONS CONSIDERED HARMFUL
Primarily assigned technology terms:
- algorithm
- ambiguity resolution
- approximation
- capitalization
- classification
- classifier
- cutoff
- data analysis
- disambiguation
- estimation procedure
- estimator
- iterative estimation
- iterative procedure
- language classification
- language classification and prediction
- language modeling
- lexical ambiguity resolution
- loglinear
- matching
- maximum likelihood
- modeling
- natural language classification
- parsing
- parsing mechanism
- part-of-speech tagging
- pos tagger
- pp attachment disambiguation
- sampling
- scoring
- scoring function
- smoothing
- statistical language modeling
- stochastic tagger
- tagger
- tagging
- tile
- unigram method
Other assigned terms:
- affix
- ambiguity
- approach
- array
- association strength
- attachment site
- brown corpus
- case
- characters
- conditional probability
- conditional probability distribution
- contextual features
- contingency table
- correlation
- correlations
- determiner
- device
- distribution
- error rate
- estimation
- evaluation data
- experimental results
- feature
- feature set
- feature vector
- feature vectors
- human parsing
- hypothesis
- inflected form
- inflection
- joint probability
- language data
- language model
- language models
- lexical ambiguity
- lexical association
- lexical features
- likelihood
- linguistic
- linguistic features
- loglinear model
- measure
- method
- morphological affix
- mutual information
- natural language
- naturm language
- noise
- nouns
- parse
- part-of-speech
- penn treebank
- phrase
- posterior
- posterior distribution
- pp attachment
- prediction accuracy
- preposition
- prepositional phrase
- prepositional phrases
- prepositions
- presupposition
- prior probability
- probabilistic model
- probabilities
- probability
- probability distribution
- probability distributions
- procedure
- process
- sentence
- sentences
- sparse data
- spoken natural language
- statistical language model
- statistical model
- statistical models
- statistical natural language
- statistics
- structural feature
- suffix
- suffixes
- symbol
- syntactic category
- tag sequence
- tagging accuracy
- tagging performance
- tags
- term
- terms
- text
- text corpus
- training
- training data
- training set
- treebank
- unigram
- verb
- verb phrase
- verb-level
- word
- word sequence
- words
