ACL RD-TEC 1.0 Summarization of W97-0322
Paper Title:
DISTINGUISHING WORD SENSES IN UNTAGGED TEXT
DISTINGUISHING WORD SENSES IN UNTAGGED TEXT
Authors: Ted Pedersen and Rebecca Bruce
Primarily assigned technology terms:
- agglomerative clustering
- algorithm
- bootstrapping
- bootstrapping approach
- classification
- classifier
- cluster analysis
- clustering
- data estimation
- decomposition
- disambiguation
- disambiguation algorithm
- em algorithm
- estimation procedure
- expectation maximization
- expectation maximization algorithm
- feature selection
- feature set selection
- feature weighting
- forward-backward algorithm
- gibbs sampling
- hidden markov
- hidden markov model
- iterative estimation
- knowledge acquisition
- language processing
- learning
- learning algorithm
- learning algorithms
- learning approaches
- majority classifier
- manufacturing
- markov model
- maximization algorithm
- maximum likelihood
- morphology
- naive bayes
- natural language processing
- nlp
- processing
- recognition
- sampling
- singular value decomposition
- speech processing
- speech recognition
- supervised learning
- supervised learning algorithm
- unsupervised disambiguation
- unsupervised learning
- unsupervised learning algorithm
- weighting
- word-sense disambiguation
Other assigned terms:
- adjective
- adjective senses
- adverb
- ambiguous word
- approach
- bayes model
- case
- class distribution
- cluster
- clusters
- co-occurrence
- co-occurrence statistics
- co-occurrences
- cohesion
- collocation
- concepts
- confusion matrix
- contemporary english
- content words
- context vector
- context vectors
- convergence
- dictionary
- dimensionality
- distribution
- estimation
- experimental results
- fact
- feature
- feature set
- feature sets
- feature space
- feature types
- interpretation
- knowledge
- knowledge acquisition bottleneck
- ldoce
- learning problem
- lexical cohesion
- likelihood
- likelihood function
- linear combination
- local maxima
- mapping
- measure
- measures
- method
- model parameters
- naive bayes model
- names
- natural language
- noise
- normal distribution
- nouns
- parametric model
- part-of-speech
- probability
- procedure
- process
- seed
- semantic
- semantic distance
- semantic network
- sense definition
- sense inventory
- senses of a word
- sentence
- sentence boundary
- sentences
- standard deviation
- statistics
- tagged text
- tags
- terms
- test set
- text
- training
- training examples
- uniform distribution
- untagged text
- verb
- verb senses
- wall street journal corpus
- window size
- word
- word co-occurrence
- word frequencies
- word senses
- wordnet
- words
- wsj corpus
