ACL RD-TEC 1.0 Summarization of P96-1043
Paper Title:
UNSUPERVISED LEARNING OF WORD-CATEGORY GUESSING RULES
UNSUPERVISED LEARNING OF WORD-CATEGORY GUESSING RULES
Primarily assigned technology terms:
- automatic learning
- boosting
- c + +
- capitalization
- categorisation
- database
- disambiguation
- induction
- learner
- learning
- learning process
- lexicalization
- morphology
- part-of-speech tagging
- rule acquisition
- rule extraction
- rule scoring
- rule-based tagger
- scoring
- search
- smoothing
- statistical acquisition
- statistical learning
- suffix tree
- tagger
- taggers
- tagging
- tagging process
- tuning
- unsupervised learning
- word guessing
- word-formation
- word-guessing
- xerox tagger
Other assigned terms:
- adjective
- affix
- affixation
- ambiguity
- approach
- bias
- brown corpus
- case
- characters
- corpus frequency
- corpus model
- distribution
- document
- english morphology
- estimation
- evaluation experiment
- evaluation methodology
- evaluations
- fact
- feature
- french
- information measure
- knowledge
- language database
- language model
- language use
- lexical resources
- lexicon
- lisp
- measure
- measures
- method
- methodology
- morphological features
- morphological rule
- morphological rules
- nouns
- part-of-speech
- parts-of-speech
- plural noun
- pos-class
- precision
- prepositions
- probabilities
- procedure
- process
- search space
- sentence
- singular noun
- stem
- stress
- sub-language
- sublanguage
- substring
- suffix
- suffixes
- tagging accuracy
- tagging performance
- technique
- text
- text corpus
- tokens
- training
- training corpus
- training data
- training examples
- training phase
- tree
- verb
- wall street journal corpus
- word
- word features
- word formation
- word frequencies
- words
