ACL RD-TEC 1.0 Summarization of W04-3249
Paper Title:
UNSUPERVISED DOMAIN RELEVANCE ESTIMATION FOR WORD SENSE DISAMBIGUATION
UNSUPERVISED DOMAIN RELEVANCE ESTIMATION FOR WORD SENSE DISAMBIGUATION
Authors: Alfio Gliozzo and Bernardo Magnini and Carlo Strapparava
Primarily assigned technology terms:
- algorithm
- bayesian classi cation
- categorization
- categorization technique
- classi cation
- ddd algorithm
- disambiguation
- disambiguation process
- domain detection
- domain driven disambiguation
- domain relevance estimation
- domain relevance extraction
- em algorithm
- expectation maximization
- expectation maximization algorithm
- frequency estimation
- gaussian mixture approach
- grouping
- indirect evaluation
- learning
- learning method
- local estimation
- maximization algorithm
- maximum likelihood
- parameter estimation
- processing
- relevance estimation
- relevance extraction
- sense disambiguation
- smoothing
- statistical estimation
- text categorization
- text processing
- unsupervised technique
- unsupervised text categorization
- unsupervised wsd
- word sense disambiguation
- wsd algorithm
Other assigned terms:
- ambiguity
- ambiguous words
- analogy
- annotation
- annotation language
- approach
- binomial distribution
- british national corpus
- case
- case information
- categorization task
- clusters
- coherence
- concept
- concepts
- conditional probability
- corpora
- data structures
- density function
- distribution
- document
- document collection
- domain information
- estimation
- events
- fact
- frequency counts
- frequency distribution
- frequency score
- gaussian mixture
- gaussian mixture model
- gaussian mixture models
- heuristic
- implementation
- interpretation
- knowledge
- labeled training data
- labeling
- lemma
- lexical resource
- lexicographer
- lexicon
- likelihood
- likelihood function
- linear combination
- local frequency count
- mapping
- measure
- method
- methodology
- mixture models
- noise
- normal distribution
- nouns
- polysemous words
- portability
- precision
- prior probability
- probabilistic framework
- probability
- probability density
- probability density function
- process
- semcor
- similarity metric
- standard deviation
- statistics
- synset
- synsets
- syntactic categories
- tagged corpus
- technique
- terms
- test data
- test set
- text
- text corpora
- text length
- theorem
- topics
- training
- training data
- transformation
- understanding
- vocabulary
- word
- word distribution
- word sense
- word senses
- wordnet
- wordnet domains
- wordnet synsets
- words
