ACL RD-TEC 1.0 Summarization of C96-2213
Paper Title:
USING A HYBRID SYSTEM OF CORPUS- AND KNOWLEDGE-BASED TECHNIQUES TO AUTOMATE THE INDUCTION OF A LEXICAL SUBLANGUAGE GRAMMAR
USING A HYBRID SYSTEM OF CORPUS- AND KNOWLEDGE-BASED TECHNIQUES TO AUTOMATE THE INDUCTION OF A LEXICAL SUBLANGUAGE GRAMMAR
Primarily assigned technology terms:
- algorithm
- binary branching
- bootstrapping
- bracketing
- clustering
- computing
- corpus-based approach
- cutoff
- decomposition
- dimension reduction
- error-driven learning
- factor analysis
- finite state
- finite state machine
- identification
- induction
- induction process
- information retrieval
- information retrieval system
- language processing
- learner
- learning
- matching
- matrix manipulation
- mining
- natural language processing
- neural net
- nlp
- nlp system
- parsing
- parsing engine
- partial parsing
- pattern matcher
- pattern matching
- processing
- reading
- recognizer
- retrieval system
- rule-based system
- search
- singular value decomposition
- subcategorization
- syntactic parsing
- syntactic processing
- tagger
- terminology
- tile
Other assigned terms:
- anchor
- approach
- bias
- characters
- clusters
- co-occurrence
- co-occurrence matrix
- context information
- cosine similarity
- cosine similarity measure
- device
- dictionary
- dimensionality
- distributional information
- fact
- feature
- finite state device
- grammar
- grammar rule
- heuristic
- interpretation
- knowledge
- large training
- lexical entries
- lexical features
- lexicon
- linguist
- linguistic
- linguists
- markov models
- measure
- measures
- method
- natural language
- noise
- nonterminals
- parse
- part of speech
- penn treebank
- phrase
- precision
- process
- pundit
- representations
- search space
- semantic
- semantic similarity
- sentence
- sentences
- similarity measure
- source text
- statistics
- structure of the sentence
- subcategorization frames
- sublanguage
- synonym
- syntactic behavior
- syntactic category
- syntactic context
- syntactic information
- tags
- technique
- term-document matrix
- terminals
- terms
- test corpus
- text
- tokens
- training
- training corpus
- training data
- transitivity
- tree
- treebank
- trees
- verb
- word
- word types
- words
