ACL RD-TEC 1.0 Summarization of W95-0104
Paper Title:
A BAYESIAN HYBRID METHOD FOR CONTEXT-SENSITIVE SPELLING CORRECTION
A BAYESIAN HYBRID METHOD FOR CONTEXT-SENSITIVE SPELLING CORRECTION
Primarily assigned technology terms:
- abductive inference
- accent restoration
- approximation
- chi-square test
- classifiers
- conflict resolution
- context-sensitive spelling
- context-sensitive spelling correction
- decision-making
- disambiguation
- discrimination procedure
- hybrid method
- lexical disambiguation
- likelihood estimate
- matching
- maximum likelihood
- pruning
- ranking
- smoothing
- spelling
- spelling correction
- spelling-correction
- tagger
- taggers
- tagging
- tile
- word disambiguation
Other assigned terms:
- accent
- ambiguity
- ambiguous word
- approach
- bayesian framework
- binary feature
- binary features
- brown corpus
- case
- coefficient
- collocation
- context window
- context words
- correlation
- correlations
- determiners
- dictionary
- disambiguation task
- discourse
- discourse topic
- distribution
- document
- fact
- feature
- french
- heuristic
- homonym
- hypothesis
- interpretation
- lexical ambiguity
- lexicon
- likelihood
- maximum likelihood estimate
- measure
- measures
- method
- noise
- nouns
- part of speech
- part-of-speech
- part-of-speech tags
- part-of-speech trigram
- part-of-speech trigram model
- parts of speech
- prediction accuracy
- prepositions
- prior probability
- probabilities
- probability
- procedure
- relation
- semantic
- sentence
- sentences
- singular noun
- sparse data
- statistics
- syntactic patterns
- syntax
- tag set
- tags
- target word
- technique
- term
- terms
- test corpus
- test phase
- text
- training
- training corpus
- training data
- training phase
- trigram
- trigram model
- user
- verb
- wall street journal text
- word
- words
