ACL RD-TEC 1.0 Summarization of P06-2084
Paper Title:
COMBINING ASSOCIATION MEASURES FOR COLLOCATION EXTRACTION
COMBINING ASSOCIATION MEASURES FOR COLLOCATION EXTRACTION
Authors: Pavel Pecina and Pavel Schlesinger
Primarily assigned technology terms:
- algorithm
- automatic collocation extraction
- bilingual word alignment
- binary classifier
- classification
- classifier
- classifiers
- clustering
- collocation extraction
- computational linguistics
- convex optimization
- cross validation
- cross-validation
- dependency parsing
- discriminant analysis
- exhaustive search
- extraction procedure
- feature selection
- feature selection algorithm
- five-fold cross validation
- hierarchical clustering
- information retrieval
- kernels
- language processing
- lemmatization
- linear discriminant
- linear discriminant analysis
- logistic regression
- loss function
- machine translation
- maximum likelihood
- measuring
- model reduction
- multivariate standardization
- natural language processing
- neural network
- neural networks
- optimization
- parsing
- part-of-speech tagging
- predictor
- preprocessing
- principal component analysis
- processing
- ranking
- regression
- regularization
- search
- selection algorithm
- significance testing
- standardization
- step-wise feature selection
- stepwise feature selection
- support vector machines
- tagging
- tuning
- validation
- visualization
- word alignment
Other assigned terms:
- annotation
- annotators
- approach
- association for computational linguistics
- association measure
- association measure performance
- association score
- bigram
- boolean vector space
- case
- cluster
- clusters
- coefficient
- collocation
- collocational expression
- compounds
- conditional probability
- confusion probability
- context similarity
- context window
- contingency table
- convergence
- correlation
- correlation coefficient
- data set
- data sets
- dependency treebank
- dependency trees
- dependency type
- dice
- distribution
- empirical results
- entropy
- estimation
- evaluation data
- events
- fact
- feature
- feature vector
- grid
- head word
- heuristic
- idiomatic expressions
- information theory
- joint probability
- kl divergence
- lexical association
- likelihood
- likelihood ratio
- linear combination
- linear model
- linguistic
- linguistics
- linguists
- manual annotation
- mean average precision
- meaning
- measure
- measures
- method
- modifier
- mutual information
- n-grams
- names
- natural language
- non-compositionality
- norm
- normal distribution
- part-of-speech
- phrase
- pointwise mutual information
- prague dependency treebank
- precision
- preposition
- probabilities
- probability
- procedure
- process
- projection
- proper names
- rank order
- regularization parameter
- scalability
- semantic
- sentences
- similarity matrix
- similarity measures
- skew divergence
- support vector
- technique
- term
- terms
- test data
- text
- text corpus
- tf \* idf
- theory
- training
- training data
- treebank
- trees
- uniform distribution
- unigram
- vector space
- verb
- wilcoxon test
- word
- word association
- word sequence
- words
