ACL RD-TEC 1.0 Summarization of W02-1004
Paper Title:
MODELING CONSENSUS: CLASSIFIER COMBINATION FOR WORD SENSE DISAMBIGUATION
MODELING CONSENSUS: CLASSIFIER COMBINATION FOR WORD SENSE DISAMBIGUATION
Authors: Radu Florian and David Yarowsky
Primarily assigned technology terms:
- 5-fold cross validation
- 5-fold cross-validation
- agglomerative clustering
- algorithm
- bayes classifier
- classification
- classifier
- classifier combination
- classifier stacking
- classifier system
- classifiers
- clustering
- comparative evaluation
- computational linguistics
- cross validation
- cross-validation
- disambiguation
- em algorithm
- evaluation framework
- evaluation system
- expectation-maximization
- feature extraction
- feature selection
- greedy training
- language processing
- learning
- learning system
- lemmatization
- maximum likelihood
- modeling
- naive bayes
- naive bayes classifier
- naive bayes classifiers
- nlp
- optimization
- parameter estimation
- part-of-speech tagger
- part-of-speech tagging
- pos tagger
- pos tagging
- probability interpolation
- processing
- ranking
- sampling
- search
- sense disambiguation
- sense disambiguation task
- sense tagging
- simulated annealing
- single classifier
- tagger
- tagging
- training algorithm
- transformation-based learning
- validation
- vector representation
- voting
- weighting
- word sense disambiguation
Other assigned terms:
- adjective
- agreement rate
- ambiguous words
- approach
- association for computational linguistics
- basque
- bigram
- case
- chunks
- class probability
- classification accuracy
- classification error
- conditional probability
- context size
- corpora
- data sets
- data structure
- disambiguation task
- distribution
- document
- empirical evaluation
- english sentence
- estimation
- extraction process
- f-measure
- fact
- feature
- feature space
- feature type
- feature types
- head noun
- heuristic
- heuristics
- interpolation
- interpolation coefficients
- lemma
- likelihood
- likelihood ratio
- linguistics
- log-likelihood
- measure
- method
- mixture models
- model performance
- n-grams
- ngram
- nouns
- optimization problem
- part of speech
- part-of-speech
- partsof-speech
- penn treebank
- polysemous words
- posterior
- posterior probability
- precision
- predicate-argument
- predicate-argument structure
- probabilities
- probability
- probability distribution
- probability distributions
- process
- regular expressions
- search space
- selectional restrictions
- sentence
- sentences
- statistics
- syntactic features
- syntactic information
- system performance
- tags
- target word
- technique
- test data
- text
- training
- training data
- training samples
- training size
- treebank
- trigram
- user
- verb
- word
- word level
- word sense
- words
