ACL RD-TEC 1.0 Summarization of J01-3001
Paper Title:
THE INTERACTION OF KNOWLEDGE SOURCES IN WORD SENSE DISAMBIGUATION
THE INTERACTION OF KNOWLEDGE SOURCES IN WORD SENSE DISAMBIGUATION
Authors: Mark Stevenson and Yorick Wilks
Primarily assigned technology terms:
- algorithm
- analyzer
- annealing algorithm
- annealing optimization
- brill tagger
- categorization
- classification
- classifiers
- computational linguistics
- computer science
- computing
- cross validation
- database
- disambiguation
- disambiguation process
- encoding
- entity identifier
- evaluation framework
- evaluation procedure
- exemplar-based learning
- extraction system
- extractor
- frequency-based sampling
- grouping
- identification
- information extraction
- information extraction system
- information retrieval
- language engineering
- learning
- learning algorithm
- learning methods
- learning system
- lexical lookup
- likelihood estimate
- machine learning
- machine learning algorithm
- machine learning methods
- machine-translation
- maximum likelihood
- memory-based learning
- memory-based learning algorithm
- modelling
- nlp
- noisy channel model
- optimization
- optimization algorithm
- parser
- part-of-speech tagger
- part-of-speech tagging
- partial disambiguation
- partial tagger
- preference resolution
- preprocessing
- reporting
- rough-grained disambiguation
- sampling
- scoring
- search
- semantic disambiguation
- semantic tagging
- sense disambiguation
- sense discrimination
- sense selection
- sense tagger
- shallow parser
- simulated annealing
- simulated annealing optimization
- smoothing
- splitting
- syntactic analyzer
- tagger
- taggers
- tagging
- unsupervised learning
- validation
- weighting
- word sense disambiguation
- wsd algorithm
Other assigned terms:
- 10-fold cross validation
- adjective
- adverb
- ambiguity
- ambiguous word
- ambiguous words
- annotated corpus
- approach
- association for computational linguistics
- baseline performance
- break
- british national corpus
- case
- collocation
- content words
- context model
- context window
- corpora
- corpus frequency
- data sparseness
- dictionaries
- dictionary
- dictionary definition
- dictionary definitions
- distance metric
- distribution
- ellipsis
- encyclopaedia
- entropy
- error rate
- evaluation corpora
- evaluation methodology
- evaluation metric
- evaluation metrics
- evaluation strategy
- exact match
- fact
- feature
- feature vector
- feature vectors
- frequency counts
- gold standard
- grammar
- grammatical categories
- grammatical category
- grammatical relations
- heuristic
- hypothesis
- implementation
- information sources
- interpretation
- knowledge
- ldoce
- lexical knowledge
- lexical resources
- lexical semantic
- lexicon
- likelihood
- linguistic
- linguistic knowledge
- linguistic phenomenon
- linguistics
- manual tagging
- mapping
- mark-up
- markup
- maximum likelihood estimate
- meaning
- meanings
- measure
- method
- methodology
- modular architecture
- named entities
- named entity
- named-entity
- names
- nlp applications
- nlp tasks
- noisy channel
- nouns
- ontology
- optimization problem
- part of speech
- part-of-speech
- part-of-speech information
- part-of-speech tag
- part-of-speech tags
- parts of speech
- penman
- penman upper model
- penn tree bank
- penn treebank
- polysemous words
- polysemy
- pp-attachment
- pragmatic information
- precision
- probabilistic models
- probabilities
- probability
- probability estimates
- procedure
- process
- proper name
- proper names
- scoring metric
- search space
- selectional preference
- selectional preferences
- selectional restrictions
- semantic
- semantic categories
- semantic class
- semantic classes
- semantic information
- semantic restriction
- semantic tags
- semcor
- senses of a word
- sentence
- sentences
- slot
- speech information
- statistical models
- statistics
- subcorpus
- surface form
- synonym
- synsets
- syntactic relations
- syntax
- tag set
- tags
- technique
- term
- terms
- test corpora
- test data
- test set
- text
- thesaurus
- tokens
- training
- training corpus
- training data
- training examples
- transformation
- transformation rules
- translation equivalents
- tree
- tree bank
- treebank
- unannotated text
- verb
- verb sense
- verb senses
- vocabulary
- word
- word corpus
- word sense
- word senses
- word types
- wordnet
- wordnet project
- wordnet synsets
- words
