ACL RD-TEC 1.0 Summarization of J98-1002
Paper Title:
SIMILARITY-BASED WORD SENSE DISAMBIGUATION
SIMILARITY-BASED WORD SENSE DISAMBIGUATION
Authors: Yael Karov and Shimon Edelman
Primarily assigned technology terms:
- algorithm
- automatic construction
- bootstrapping
- bootstrapping process
- classifier
- clustering
- computational learning
- computational linguistics
- computer science
- computing
- disambiguation
- disambiguation algorithm
- disambiguation process
- grouping
- illustration
- induction
- iterative algorithm
- iterative estimation
- iterative process
- knowledge acquisition
- language modeling
- learning
- learning process
- modeling
- nearest neighbors
- normalization
- pattern recognition
- probabilistic language modeling
- recognition
- sense disambiguation
- sense tagging
- similarity computation
- similarity evaluation
- smoothing
- statistical pattern recognition
- tagging
- terminology
- tuning
- visualization
- voting
- word sense disambiguation
Other assigned terms:
- adjective
- ambiguous word
- ambiguous words
- approach
- association for computational linguistics
- bias
- bilingual corpora
- bilingual corpus
- bilingual lexicon
- british national corpus
- case
- cluster
- clusters
- co-occurrence
- co-occurrence information
- co-occurrence statistics
- co-occurrences
- cognitive
- concepts
- context features
- context similarity
- context words
- contextual similarity
- convergence
- corpora
- correlation
- data set
- dictionaries
- dictionary
- dictionary definition
- disambiguation task
- discourse
- distance metric
- estimation
- external knowledge
- external knowledge source
- fact
- feature
- feature space
- hierarchical structure
- hypothesis
- induction hypothesis
- knowledge
- knowledge acquisition bottleneck
- large corpora
- large corpus
- lexical category
- lexicon
- likelihood
- linguistics
- log-likelihood
- machine-readable dictionary
- manual intervention
- manual translation
- maps
- mathematics
- meaning
- meanings
- measure
- measures
- method
- monolingual corpus
- n-grams
- noise
- nouns
- part of speech
- part-of-speech
- polysemous word
- polysemous words
- probability
- probability density
- process
- relation
- seed
- seed words
- semantic
- semantic hierarchy
- semantic network
- sense distinctions
- sense information
- senses of a word
- sentence
- sentence similarity
- sentence structure
- sentences
- similarity between words
- similarity matrix
- similarity measure
- similarity measures
- sparse data
- statistics
- synonyms
- synsets
- syntactic information
- tags
- target word
- technique
- test data
- text
- text corpora
- text corpus
- theorem
- thesaurus
- topics
- training
- training corpus
- training data
- training examples
- training phase
- training set
- transitivity
- translations
- tree
- untagged corpus
- user
- verb
- word
- word sense
- word similarity
- wordnet
- wordnet similarity
- words
