ACL RD-TEC 1.0 Summarization of N01-1023
Paper Title:
APPLYING CO-TRAINING METHODS TO STATISTICAL PARSING
APPLYING CO-TRAINING METHODS TO STATISTICAL PARSING
Primarily assigned technology terms:
- active learning
- adaboost
- algorithm
- analyzer
- backoff smoothing
- bootstrap
- bracketing
- classification
- classifiers
- clustering
- co-training
- co-training algorithm
- computing
- cutoff
- decision trees
- decomposition
- dependency analyzer
- disambiguation
- document classification
- hand tuning
- hidden markov
- hidden markov models
- hmms
- hypothesis testing
- identification
- inside-outside algorithm
- iterative algorithm
- iterative method
- language modeling
- learning
- learning algorithm
- learning technique
- learning techniques
- lexicalization
- machine learning
- machine learning techniques
- modeling
- named-entity identification
- named-entity recognition
- nlp
- page classification
- parser
- parsers
- parsing
- part-of-speech tagger
- part-of-speech tagging
- pos tagger
- pos tagging
- processing
- pruning
- ranking
- recognition
- recognizer
- sample selection
- scoring
- search
- sense disambiguation
- smoothing
- speech recognizer
- statistical parser
- statistical parsers
- statistical parsing
- subcategorization
- supertagging
- tagger
- tagging
- text classification
- tuning
- web page classification
- word sense disambiguation
- word-sense disambiguation
Other assigned terms:
- adjunction
- ambiguity
- annotation
- approach
- backoff
- backoff model
- baseline model
- beam
- beam size
- brown corpus
- cache
- case
- classification problem
- classification tasks
- conditional independence
- context window
- data set
- derivation
- derivation tree
- derivations
- dictionaries
- dictionary
- discourse
- distributional information
- document
- elementary tree
- empirical results
- error rate
- evaluations
- formalism
- generative model
- grammar
- grammars
- heuristics
- hypothesis
- labeled training data
- labeling
- lattice
- learnability
- lexical coverage
- lexical information
- lexicalized grammar
- lexicalized structure
- lexicalized tree
- likelihood
- local context
- ltag formalism
- markov models
- method
- methodology
- named-entity
- nlp tasks
- noun phrases
- parameter space
- parse
- parse tree
- part of speech
- part-of-speech
- penn treebank
- phrase
- phrase structure
- pos tag
- precision
- predicate-argument
- predicate-argument structure
- probabilistic models
- probabilities
- probability
- probability model
- procedure
- process
- punctuation
- relation
- representations
- root node
- search space
- seed
- sentence
- sentences
- sparse data
- speech tag
- statistical model
- statistical models
- style
- subcategorization frames
- tags
- technique
- terms
- test data
- test set
- text
- theorem
- tokens
- training
- training data
- training examples
- training set
- tree
- tree adjoining grammar
- treebank
- treebank wsj corpus
- trees
- trigram
- trigram model
- understanding
- unlabeled text
- wall street journal corpus
- web page
- web pages
- word
- word error rate
- word sense
- word senses
- words
- wsj corpus
