ACL RD-TEC 1.0 Summarization of J93-1003
Paper Title:
ACCURATE METHODS FOR THE STATISTICS OF SURPRISE AND COINCIDENCE
ACCURATE METHODS FOR THE STATISTICS OF SURPRISE AND COINCIDENCE
Primarily assigned technology terms:
- approximation
- computational linguistics
- computing
- frequency weighting
- illustration
- indexing
- information retrieval
- language processing
- latent semantic indexing
- machine translation
- natural language processing
- phrasing
- processing
- random selection
- ranking
- semantic indexing
- shallow information retrieval
- statistical analysis
- statistical approaches
- statistical methods
- statistical test
- symbolic algebra
- text analysis
- text retrieval
- weighting
Other assigned terms:
- approach
- association for computational linguistics
- bigram
- binomial distribution
- break
- case
- contingency table
- convergence
- correlation
- derivations
- discourse
- distribution
- document
- document frequency
- english language
- english text
- events
- fact
- feature
- hypotheses
- hypothesis
- implementation
- intention
- inverse document frequency
- large corpus
- latent semantic
- likelihood
- likelihood function
- likelihood ratio
- linguistics
- log-likelihood
- log-likelihood ratio
- measure
- measures
- model parameters
- mood
- mutual information
- natural language
- normal distribution
- notational brevity
- null hypothesis
- pairs of words
- parameter space
- parameter spaces
- probabilities
- probability
- probability density
- query
- semantic
- statistic
- statistical model
- statistical significance
- statistics
- technique
- terms
- text
- vocabulary
- word
- word frequencies
- words
- z-score
