ACL RD-TEC 1.0 Summarization of P93-1022
Paper Title:
CONTEXTUAL WORD SIMILARITY AND ESTIMATION FROM SPARSE DATA
CONTEXTUAL WORD SIMILARITY AND ESTIMATION FROM SPARSE DATA
Authors: Ido Dagan and Shaul Marcus and Shaul Markovitch
Primarily assigned technology terms:
- approximation
- classification
- computing
- data base
- data recovery
- disambiguation
- disambiguation method
- estimation method
- estimator
- frequency method
- inferencing
- language processing
- likelihood estimator
- machine translation
- maximum likelihood
- maximum likelihood estimator
- measuring
- natural language processing
- normalization
- parsing
- processing
- random selection
- search
- semantic classification
- sense disambiguation
- sense selection
- similarity method
- similarity-based estimation
- smoothing
- smoothing method
- syntactic parsing
- target word selection
- tuning
- weighting
- word selection
- word sense disambiguation
Other assigned terms:
- ambiguity
- analogy
- approach
- bias
- bigram
- bilingual corpus
- bilingual lexicon
- case
- context similarity
- context words
- contextual word
- corpora
- cpu time
- data sparseness
- determiners
- disambiguation task
- estimation
- evaluations
- events
- fact
- function words
- heuristic
- implementation
- interpretation
- large training
- lexicon
- likelihood
- linear order
- linguistic
- linguistic data
- measure
- measures
- method
- mutual information
- n-grams
- natural language
- noise
- normalization factor
- phrase
- precision
- prepositions
- probabilities
- probability
- probability estimates
- procedure
- relation
- semantic
- sentence
- sentences
- similarity measure
- similarity metric
- sparse data
- sparse data problem
- statistical data
- syntactic relations
- target language
- target word
- technique
- term
- terms
- text
- theories
- training
- training corpus
- training data
- translations
- word
- word classes
- word frequencies
- word frequency
- word sense
- word similarity
- words
