ACL RD-TEC 1.0 Summarization of A00-1031

Other assigned terms:

• ambiguity
• ambiguity rate
• annotated corpora
• annotation
• approach
• argumentation
• beam
• capitalization information
• case
• characters
• conditional probabilities
• corpora
• distribution
• english corpus
• entropy
• evaluations
• fact
• frequency counts
• generation
• grammatical functions
• interpolation
• interpretation
• language models
• lexicon
• likelihood
• likelihood probability
• markov models
• maximum likelihood estimate
• method
• n-gram
• names
• negra
• negra corpus
• nouns
• opinion
• part-of-speech
• part-of-speech annotation
• part-of-speech tags
• parts-ofspeech
• penn treebank
• predicate-argument
• predicate-argument structures
• probabilities
• probability
• probability distribution
• probability distributions
• procedure
• process
• processing time
• proper names
• punctuation
• punctuation marks
• research topic
• sentence
• sentence boundaries
• sentences
• size of the corpus
• standard deviation
• stem
• suffix
• suffixes
• susanne corpus
• tagged corpus
• tagging accuracy
• tags
• tagset
• technique
• term
• test corpus
• test data
• test set
• text
• tokens
• training
• training corpora
• training corpus
• training data
• training set
• transition probabilities
• treebank
• trigram
• word
• word classes
• words