ACL RD-TEC 1.0 Summarization of P98-2148
Paper Title:
A STOCHASTIC LANGUAGE MODEL USING DEPENDENCY AND ITS IMPROVEMENT BY WORD CLUSTERING
A STOCHASTIC LANGUAGE MODEL USING DEPENDENCY AND ITS IMPROVEMENT BY WORD CLUSTERING
Authors: Shinsuke Mori and Makoto Nagao
Primarily assigned technology terms:
- algorithm
- analyzer
- clustering
- clustering method
- greedy algorithm
- interpolation method
- interpolation technique
- language modeling
- language processing
- learning
- modeling
- natural language processing
- parser
- parsers
- parsing
- parsing method
- pos estimation
- processing
- recognition
- recognition system
- reporting
- rule-based analyzer
- search
- search algorithm
- solution search
- speech recognition
- stochastic language modeling
- syntactic analysis
- syntactic analyzer
- tagger
- word clustering
- word-clustering
Other assigned terms:
- alphabet
- annotated corpus
- binary relation
- bunsetsu
- case
- character sequence
- characters
- class-based dependency model
- class-based model
- concept
- content words
- context-free grammar
- corpus size
- cross entropy
- dependency model
- dependency relation
- dependency relations
- derivation
- derivation tree
- derivations
- distribution
- edr corpus
- entropy
- estimation
- experimental results
- fact
- function word
- function words
- generation
- grammar
- grammars
- interpolation
- interpolation coefficients
- japanese language
- language model
- language models
- lexicalized model
- lexicon
- linguistic
- linguistic phenomena
- method
- methodology
- n-gram
- n-gram model
- n-gram models
- natural language
- normal form
- parsing accuracy
- perplexity
- pos-based model
- posterior
- predictive power
- probabilities
- probability
- probability value
- process
- punctuation
- relation
- sentence
- sentences
- stochastic context-free grammar
- stochastic language model
- symbol
- symbols
- syntactic behavior
- syntactic tree
- technique
- terminals
- terms
- test corpus
- tree
- uniform distribution
- unknown word model
- verb
- word
- word model
- word n-gram model
- word sequence
- word sequences
- words
- writing system
