ACL RD-TEC 1.0 Summarization of P98-2251
Paper Title:
PREDICTING PART-OF SPEECH INFORMATION ABOUT UNKNOWN WORDS USING STATISTICAL METHODS
PREDICTING PART-OF SPEECH INFORMATION ABOUT UNKNOWN WORDS USING STATISTICAL METHODS
Primarily assigned technology terms:
- approximation
- capitalization
- cross-validation
- heuristic method
- hidden markov
- hidden markov model
- hmm tagger
- hyphenation
- markov model
- maximum entropy
- morphological process
- parsing
- part-of-speech tagger
- part-of-speech tagging
- partial parsing
- predictor
- processing
- smoothing
- statistical methods
- tagger
- tagging
- tagging system
- word prediction
Other assigned terms:
- 10-fold cross-validation
- adjective
- affix
- affixation
- affixes
- approach
- brown corpus
- case
- characters
- concept
- confidence measure
- contextual information
- distribution
- entropy
- entropy models
- feature
- feature information
- heuristic
- hmm model
- information sources
- knowledge
- lexicon
- lexicon entry
- likelihood
- linguistic
- linguistic information
- maximum entropy models
- measure
- method
- morphological information
- nouns
- part-of-speech
- part-of-speech information
- parts of speech
- past participle
- penn treebank
- penn treebank project
- prefixes and suffixes
- probabilistic lexicon
- probabilities
- probability
- probability distribution
- process
- sentence
- sentences
- statistical data
- suffix
- suffixes
- syntactic categories
- tagged corpus
- tags
- technique
- test set
- training
- training corpus
- training data
- training set
- treebank
- treebank project
- verb
- word
- words
