ACL RD-TEC 1.0 Summarization of E99-1026
Paper Title:
JAPANESE DEPENDENCY STRUCTURE ANALYSIS BASED ON MAXIMUM ENTROPY MODELS
JAPANESE DEPENDENCY STRUCTURE ANALYSIS BASED ON MAXIMUM ENTROPY MODELS
Authors: Kiyotaka Uchimoto and Satoshi Sekine and Hitoshi Isahara
Primarily assigned technology terms:
- algorithm
- analysis method
- automatic feature selection
- beam search
- boosting
- bunsetsu identification
- computational linguistics
- corpus-based approach
- decision tree
- dependency analysis
- dependency structure analysis
- entropy estimation
- estimation process
- feature selection
- identification
- japanese sentence analysis
- language modeling
- learning
- maximum entropy
- maximum entropy framework
- maximum entropy model
- maximum likelihood
- modeling
- morphological analysis
- parser
- parsers
- parsing
- preprocessing
- probability estimation
- rule-based approach
- search
- sentence analysis
- statistical approaches
- statistical language modeling
- structure analysis
- tokenization
Other assigned terms:
- adjective
- approach
- beam
- bunsetsu
- bunsetsus
- case
- conditional probability
- corpora
- data sparseness
- data sparseness problem
- dependency likelihood
- dependency model
- dependency structure
- edr corpus
- entropy
- entropy formulation
- entropy models
- estimation
- feature
- feature set
- feature sets
- feature type
- function word
- head word
- idiomatic expressions
- index
- inflection
- japanese dependency
- japanese dependency structure
- japanese sentences
- kyoto university corpus
- kyoto university text corpus
- lexical features
- lexical information
- likelihood
- linguistics
- maximum entropy models
- method
- paragraph
- parsing accuracy
- part-of-speech
- part-of-speech tag
- particle
- particles
- parts of speech
- posterior
- probabilities
- probability
- probability model
- process
- punctuation
- running time
- search space
- segments
- sentence
- sentences
- sparseness problem
- statistics
- suffix
- tagged corpus
- tags
- technique
- term
- terms
- test corpus
- test data
- text
- text corpus
- training
- training corpus
- training data
- training set
- tree
- verb
- word
- words
