ACL RD-TEC 1.0 Summarization of W00-1303
Paper Title:
JAPANESE DEPENDENCY STRUCTURE ANALYSIS BASED ON SUPPORT VECTOR MACHINES
JAPANESE DEPENDENCY STRUCTURE ANALYSIS BASED ON SUPPORT VECTOR MACHINES
Authors: Taku Kudo and Yuji Matsumoto
Primarily assigned technology terms:
- algorithm
- approximation
- beam search
- binary classifier
- boosting
- bottom-up algorithm
- bottom-up parsing
- bottom-up parsing algorithm
- categorization
- classification
- classifier
- classifiers
- cyk algorithm
- data selection
- decision trees
- dependency analysis
- dependency structure analysis
- efficient parsing
- feature selection
- identification
- japanese dependency analysis
- japanese sentence analysis
- kernel
- language processing
- learning
- learning algorithms
- learning framework
- learning techniques
- local optimization
- machine learning
- maximum entropy
- maximum entropy framework
- natural language processing
- optimization
- parser
- parsing
- parsing algorithm
- parsing technique
- pattern recognition
- polynomial kernel
- probabilistic parsing
- probability function
- processing
- recognition
- sample selection
- search
- searching
- sentence analysis
- statistical learning
- statistical parsing
- structure analysis
- structure identification
- support vector machines
- syntactic structure analysis
- text categorization
- voting
Other assigned terms:
- adverb
- ambiguity
- approach
- beam
- bracketed corpus
- bunsetsu
- case
- chunk
- chunks
- computational complexity
- computational overhead
- conditional probability
- corpora
- data sparseness
- data sparseness problem
- dependency pattern
- dependency relation
- dependency relations
- dependency structure
- dependency structures
- dimensionality
- distance measure
- entropy
- entropy models
- experimental results
- feature
- feature set
- feature space
- feature vector
- functional word
- inflection
- japanese dependency
- japanese dependency structure
- japanese sentences
- kernel function
- kyoto university corpus
- kyoto university text corpus
- learning model
- lexical entries
- linguistic
- linguistic features
- mapping
- maximum entropy models
- measure
- method
- modifier
- natural language
- noise
- optimization problem
- parsing accuracy
- parsing models
- parsing process
- part-of-speech
- particle
- particles
- parts-of-speech
- positive and negative examples
- predicates
- probabilities
- probability
- probability model
- probability value
- process
- projection
- punctuation
- punctuation marks
- relation
- segments
- sentence
- sentences
- sigmoid function
- sparseness problem
- statistical model
- support vector
- svms
- syntactic ambiguity
- syntactic structure
- tagged corpora
- tags
- technique
- term
- terms
- test data
- text
- text corpus
- training
- training data
- training examples
- training phase
- training time
- tree-bank
- trees
- verb
- word
- words
