ACL RD-TEC 1.0 Summarization of H89-2013
Paper Title:
ENHANCED GOOD-TURING AND CAT.CAL: TWO NEW METHODS FOR ESTIMATING PROBABILITIES OF ENGLISH BIGRAMS (ABBREVIATED VERSION)
ENHANCED GOOD-TURING AND CAT.CAL: TWO NEW METHODS FOR ESTIMATING PROBABILITIES OF ENGLISH BIGRAMS (ABBREVIATED VERSION)
Authors: Kenneth W. Church and William A. Gale
Primarily assigned technology terms:
- categorization
- character recognition
- estimator
- good-turing method
- grouping
- ibm speech recognition
- language modeling
- likelihood estimator
- maximum likelihood
- maximum likelihood estimator
- modeling
- optical character recognition
- pattern recognition
- predictor
- processing
- qualitative evaluation
- quantitative evaluation
- recognition
- smoothing
- speech recognition
Other assigned terms:
- acronym
- adjective
- bigram
- bigram model
- biology
- brown corpus
- case
- characters
- corpora
- distribution
- estimation
- fact
- feature
- inferences
- interpolation
- language model
- language models
- likelihood
- measure
- method
- methodology
- n-gram
- n-gram model
- n-grams
- ngram
- pairs of words
- paragraphs
- probabilities
- probability
- probability estimates
- process
- punctuation
- sentences
- standard deviation
- statistical significance
- term
- test corpora
- test corpus
- text
- tokens
- training
- training corpus
- training text
- trigram
- trigram model
- unigram
- unigram model
- vocabulary
- vocabulary size
- word
- words