ACL RD-TEC 1.0 Summarization of P97-1008
Paper Title:
SIMILARITY-BASED METHODS FOR WORD SENSE DISAMBIGUATION
SIMILARITY-BASED METHODS FOR WORD SENSE DISAMBIGUATION
Authors: Ido Dagan and Lillian Lee and Fernando Pereira
Primarily assigned technology terms:
- a statistical part-of-speech
- back-off smoothing
- bigram language modeling
- clustering
- cooccurrence smoothing
- corresponding training
- cross-validation
- disambiguation
- disambiguation method
- disambiguation problem
- distributional clustering
- estimator
- grouping
- language modeling
- language processing
- likelihood estimate
- matching
- maximum likelihood
- maximum-likelihood
- maximum-likelihood estimation
- measuring
- modeling
- natural language processing
- normalization
- part-of-speech tagger
- part-of-speech tagging
- pattern matching
- probability redistribution
- processing
- search
- sense disambiguation
- sense disambiguation task
- similarity-based estimation
- similarity-based language modeling
- similarity-based smoothing
- smoothing
- smoothing method
- statistical language processing
- statistical methods
- statistical part-of-speech tagger
- tagger
- tagging
- tuning
- weighting
- word sense disambiguation
Other assigned terms:
- ambiguous word
- approach
- back-off model
- bigram
- case
- cluster
- conditional distribution
- conditional probability
- confusion probability
- data sparseness
- dictionaries
- disambiguation task
- distribution
- distributional similarity
- error rate
- estimation
- events
- experimental results
- experimental setting
- fact
- grid
- interpolation
- joint distribution
- kl divergence
- knowledge
- language model
- language models
- large training
- likelihood
- linear combination
- linguistic
- maximum likelihood estimate
- measure
- measures
- method
- natural language
- norm
- normalization factor
- nouns
- part-of-speech
- perplexity
- probabilities
- probability
- probability distributions
- probability estimates
- sense disambiguation problem
- sense distinctions
- sentence
- sentence fragment
- similarity between words
- similarity function
- similarity measures
- similarity model
- sparse data
- statistics
- terms
- test corpus
- test data
- test set
- training
- training corpus
- training data
- training set
- unigram
- unigram probability
- verb
- weighting scheme
- word
- word classes
- word frequency
- word pair
- word sense
- word similarity
- words
