ACL RD-TEC 1.0 Summarization of P03-1004
Paper Title:
FAST METHODS FOR KERNEL-BASED TEXT ANALYSIS
FAST METHODS FOR KERNEL-BASED TEXT ANALYSIS
Authors: Taku Kudo and Yuji Matsumoto
Primarily assigned technology terms:
- algorithm
- approximation
- basenp chunking
- binary classification
- c + +
- cascaded chunking
- chunking
- classification
- classification algorithm
- classifier
- classifiers
- cubic kernel
- database
- dependency parser
- dependency parsing
- depth-first search
- efficient parsing
- english basenp chunking
- entity recognition
- feature combination
- feature expansion
- feature selection
- indexing
- information retrieval
- inverted indexing
- inverted representation
- japanese dependency parser
- japanese dependency parsing
- japanese word segmentation
- kernel
- kernel-based learning
- kernels
- language processing
- learning
- linear kernel
- machine learning
- majority voting
- mapping function
- maximum entropy
- maximum entropy model
- mining
- mining task
- named entity recognition
- named-entity recognizer
- natural language processing
- nlp
- pairwise classification
- parser
- parsing
- parsing algorithm
- part-of-speech tagging
- pattern mining
- polynomial kernel
- processing
- pruning
- question answering
- recognition
- recognizer
- rule-based system
- search
- segmentation
- sequential pattern mining
- sub-structure mining
- subset mining
- support vector machines
- tagging
- text analysis
- text chunking
- text mining
- voting
- word segmentation
Other assigned terms:
- approach
- basenp
- binary classification problem
- binary feature
- boundary marker
- bunsetsu
- cascaded chunking model
- case
- character type
- characters
- chinese characters
- chunk
- chunking model
- chunks
- classification problem
- classification task
- data set
- dependency relation
- dependency relations
- english basenp
- entropy
- experimental results
- feature
- feature set
- feature sets
- feature space
- feature structures
- feature vector
- feature vectors
- formalization
- index
- inverted index
- japanese dependency
- japanese sentences
- japanese word
- katakana
- kernel function
- kyoto university corpus
- lemma
- lexical entries
- linguistic
- linguistic features
- mapping
- maps
- method
- methodology
- modifier
- named entity
- named-entity
- natural language
- nlp tasks
- noun phrases
- part-of-speech
- phrase
- process
- quadratic kernel
- relation
- running time
- sentence
- sentences
- structure of a sentence
- support vector
- svms
- tagging task
- tags
- terms
- test data
- text
- training
- training and test data
- training data
- training examples
- word
- word boundaries
- words
- wsj corpus
