ACL RD-TEC 1.0 Summarization of W94-0112
Paper Title:
BOOTSTRAPPING STATISTICAL PROCESSING INTO A RULE-BASED NATURAL LANGUAGE PARSER
BOOTSTRAPPING STATISTICAL PROCESSING INTO A RULE-BASED NATURAL LANGUAGE PARSER
Primarily assigned technology terms:
- algorithm
- bootstrapping
- bootstrapping method
- chart parser
- chart parsing
- chart parsing algorithm
- coding
- computational linguistics
- computer system
- computing
- cutoff
- language parser
- natural language parser
- nlp
- nlp system
- nlp systems
- normalization
- parser
- parsers
- parsing
- parsing algorithm
- processing
- regression
- search
- searching
- statistical methods
- statistical nlp
- statistical processing
- subcategorization
- tagging
- terminology
- the chart parsing
- tuning
- verb subcategorization
Other assigned terms:
- ambiguity
- annotated corpora
- approach
- augmented phrase
- augmented phrase structure
- best-first strategy
- brown corpus
- case
- community
- corpora
- dictionary
- dictionary data
- english grammar
- estimation
- extraction process
- fact
- feature
- grammar
- grammar rules
- independence assumption
- input string
- input text
- knowledge
- language models
- large corpora
- large corpus
- lexicon
- linguist
- linguistic
- linguistic information
- linguistic knowledge
- linguistic structures
- linguistics
- linguists
- manual tagging
- measures
- method
- natural language
- online dictionary
- parameter space
- parse
- parse tree
- parsing process
- part of speech
- part-of-speech
- parts of speech
- parts-of-speech
- partsof-speech
- phrase
- phrase attachment
- phrase structure
- phrase structure grammar
- prepositional phrase
- prepositional phrase attachment
- probabilities
- probability
- process
- rule set
- search space
- segments
- sentence
- sentences
- statistical approach
- statistical information
- statistical model
- statistics
- sub-tree
- subcategorization frames
- subtree
- subtrees
- syntactic function
- syntactic parse
- syntactic structure
- tags
- term
- text
- text corpora
- text segments
- textbook
- training
- training data
- tree
- tree structures
- trees
- trigram
- unification-based grammar
- untagged corpora
- untagged corpus
- verb
- word
- words
