ACL RD-TEC 1.0 Summarization of C00-1081
Paper Title:
A STOCHASTIC PARSER BASED ON A STRUCTURAL WORD PREDICTION MODEL
A STOCHASTIC PARSER BASED ON A STRUCTURAL WORD PREDICTION MODEL
Authors: Shinsuke MORI and Masafumi NISHIMURA and Nobuyasu ITOH and Shiho OGINO and Hideo WATANABE
Primarily assigned technology terms:
- algorithm
- analyzer
- em algorithm
- final state
- finite state
- hidden markov
- hidden markov model
- identification
- interpolation method
- interpolation technique
- language modeling
- language processing
- language understanding
- learning
- lexicalization
- lexicalized parser
- likelihood estimation
- markov model
- modeling
- natural language processing
- parameter estimation
- parser
- parsers
- parsing
- pos tagging
- processing
- reading
- recognition
- recognizer
- search
- search algorithm
- segmentation
- smoothing
- smoothing method
- solution search
- speech recognition
- speech recognizer
- spoken language understanding
- stochastic language modeling
- syntactic analysis
- syntactic analyzer
- tagger
- taggers
- tagging
- tile
- viterbi
- viterbi algorithm
- word prediction
Other assigned terms:
- ambiguity
- approach
- bunsetsu
- case
- case frame
- character sequence
- characters
- content words
- context-free grammar
- corpus size
- cross entropy
- dependency model
- dependency relation
- dependency relations
- dependency structure
- dependency tree
- derivations
- distribution
- entropy
- estimation
- events
- experimental results
- fact
- finite state model
- frame
- grammar
- head word
- interpolation
- japanese dependency
- japanese language
- japanese sentences
- language model
- language models
- language structure
- lexica
- lexicalized model
- lexicon
- likelihood
- linguists
- method
- n-gram
- n-gram model
- n-gram models
- natural language
- natural languages
- parse
- parse tree
- parsing accuracy
- part-of-speech
- partial parse
- partial parse tree
- pos-based model
- prediction model
- predictive power
- probabilities
- probability
- process
- relation
- sentence
- sentences
- spoken language
- stochastic language model
- stochastic model
- structure of a sentence
- subtrees
- technique
- terms
- test corpus
- text
- training
- training corpus
- training data
- transition probability
- tree
- trees
- understanding
- uniform distribution
- unknown word model
- vocabulary
- word
- word model
- word sequence
- word string
- words
