ACL RD-TEC 1.0 Summarization of P06-1054
Paper Title:
A FAST, ACCURATE DETERMINISTIC PARSER FOR CHINESE
A FAST, ACCURATE DETERMINISTIC PARSER FOR CHINESE
Authors: Mengqiu Wang and Kenji Sagae and Teruko Mitamura
Primarily assigned technology terms:
- adaboost
- algorithm
- automatic tagging
- binary classification
- boosting
- chinese constituency parsing
- chinese constituent parsing
- chinese parsing
- classification
- classification process
- classification technique
- classifier
- classifier ensemble
- classifier stacking
- classifiers
- computational linguistics
- constituency parsing
- constituent parsing
- corpus preparation
- data-oriented parsing
- decision tree
- decision tree classifier
- decision trees
- deterministic parser
- deterministic parsing
- disambiguation
- discriminative classification
- discriminative classification technique
- feature selection
- final state
- inside-outside unsupervised learning algorithm
- kernel
- language learning
- learner
- learning
- learning algorithm
- learning approaches
- learning technique
- lexicalization
- machine learning
- maxent
- maximum-entropy
- maximum-entropy modeling
- memory-based learner
- memory-based learning
- modeling
- natural language learning
- nlp
- parameter estimation
- parser
- parsers
- parsing
- parsing algorithm
- pcfg parser
- polynomial kernel
- pos tagger
- pos tagging
- preprocessing
- regularization
- resampling
- risk minimization
- scoring
- segmentation
- semantic parsing
- shallow parsing
- single classifier
- smoothing
- statistical decision tree
- support vector machine
- svm classifier
- tagger
- tagging
- text segmentation
- transformation-based learning
- tree classifier
- unsupervised learning
- unsupervised learning algorithm
- verb phrases
- voting
Other assigned terms:
- approach
- association for computational linguistics
- binary classification problem
- binary features
- binary tree
- branching trees
- case
- characters
- chinese text
- chinese treebank
- classification accuracy
- classification error
- classification error rate
- classification problem
- classification task
- classifier model
- contextual features
- cpu time
- data structures
- dependency model
- dependency structures
- development set
- distribution
- empty nodes
- english penn treebank
- entropy
- error rate
- estimation
- evaluation metrics
- fact
- feature
- feature set
- gaussian prior
- grammar
- head-word
- heuristic
- heuristic rules
- implementation
- lexical features
- linear time
- linguistics
- maps
- maxent model
- maximum-entropy model
- measure
- measures
- method
- names
- natural language
- nonterminal
- nouns
- parse
- parse state
- parse tree
- parser performance
- parsing accuracy
- parsing model
- parsing process
- parsing task
- part-of-speech
- part-of-speech tags
- partial parse
- partial parse tree
- pcfg
- pcfg model
- penn chinese treebank
- penn treebank
- phrase
- pos sequence
- pos tag
- precision
- probability
- probability distribution
- probability estimate
- process
- proper noun
- punctuation
- risk minimization principle
- runtime
- semantic
- sentence
- sentences
- subtree
- support vector
- svm model
- symbols
- tagging accuracy
- tags
- technique
- terms
- test set
- text
- time complexity
- toolkit
- training
- training data
- training examples
- training set
- transformation
- tree
- tree node
- tree-adjoining grammar
- treebank
- trees
- verb
- word
- words
