ACL RD-TEC 1.0 Summarization of P95-1039
Paper Title:
TAGSET REDUCTION WITHOUT INFORMATION LOSS
TAGSET REDUCTION WITHOUT INFORMATION LOSS
Primarily assigned technology terms:
- algorithm
- best-first search
- capitalization
- cluster selection
- clustering
- clustering algorithm
- disambiguation
- hidden markov
- hidden markov models
- hmms
- identification
- parameter estimation
- part-of-speech disambiguation
- part-of-speech tagging
- probability estimation
- processing
- search
- tagger
- tagging
- training procedure
- trigram training
Other assigned terms:
- adjective
- break
- cluster
- clusters
- co-occurrence
- corpora
- determiner
- distribution
- estimation
- fact
- frequency counts
- frequency distribution
- lexemes
- lexicon
- local maximum
- markov models
- measure
- method
- n-gram
- n-gram model
- n-gram models
- nouns
- part of speech
- part-of-speech
- parts of speech
- polynomial time
- posteriori probability
- probabilities
- probability
- probability distributions
- probability estimates
- procedure
- similarity measure
- sparse data
- sparse data problem
- statistical model
- susanne corpus
- tag information
- tagging accuracy
- tags
- tagset
- technique
- text
- text corpus
- training
- training corpus
- trigram
- word
- words
