ACL RD-TEC 1.0 Summarization of J97-3003
Paper Title:
AUTOMATIC RULE INDUCTION FOR UNKNOWN-WORD GUESSING
AUTOMATIC RULE INDUCTION FOR UNKNOWN-WORD GUESSING
Primarily assigned technology terms:
- algorithm
- bootstrap
- brill tagger
- c + +
- capitalization
- categorization
- classification
- computational linguistics
- database
- disambiguation
- document categorization
- final state
- guessing-rule induction
- hmm tagger
- induction
- induction process
- instantiation
- learner
- learning
- learning process
- lexicalization
- listing
- measuring
- morphology
- nlp
- parsers
- parsing
- part-of-speech tagging
- pruning
- rating
- robust parsing
- rule acquisition
- rule extraction
- rule induction
- rule scoring
- rule-based tagger
- rule-induction
- sampling
- scoring
- search
- statistical acquisition
- statistical learning
- statistical rule induction
- stochastic tagger
- suffix tree
- tagger
- taggers
- tagging
- tagging algorithm
- tagging process
- tokenization
- word-guessing
- xerox tagger
Other assigned terms:
- adjective
- affix
- affixation
- ambiguity
- annotated corpora
- annotated corpus
- annotated training corpus
- annotation
- approach
- bias
- bigram
- brown corpus
- case
- characters
- coefficient
- corpora
- corpus frequency
- dictionary
- distribution
- document
- dutch
- empty string
- english lexicon
- english morphology
- error rate
- estimation
- evaluation methodology
- evaluation metrics
- evaluations
- fact
- feature
- foreign word
- french
- frequency counts
- general-purpose lexicon
- heuristic
- index
- information measure
- interpretation
- knowledge
- language use
- large training
- lexical categories
- lexical database
- lexical entries
- lexical resources
- lexicon
- lexicon entries
- lexicon entry
- linguistics
- lisp
- manual annotation
- markup
- measure
- measures
- method
- methodology
- morphological annotation
- morphological features
- morphological rule
- morphological rules
- morphological structure
- noise
- normal distribution
- noun category
- nouns
- part of speech
- part-of-speech
- part-of-speech tags
- penn treebank
- penn treebank tag
- penn treebank tag set
- plural noun
- pos-class
- precision
- prefixes and suffixes
- probabilities
- probability
- process
- proper noun
- rule set
- rule sets
- search space
- segments
- sentence
- singular noun
- statistics
- stem
- stems
- subcorpus
- substring
- suffix
- suffixes
- tag set
- tagging accuracy
- tagging performance
- tags
- technique
- terms
- test collection
- test data
- text
- textbook
- training
- training and test data
- training corpus
- training data
- training examples
- training phase
- transformation
- tree
- treebank
- treebank tag set
- untagged corpus
- verb
- word
- word classes
- word features
- word formation
- word formation rules
- word frequencies
- word usage
- words
