ACL RD-TEC 1.0 Summarization of A97-1004
Paper Title:
A MAXIMUM ENTROPY APPROACH TO IDENTIFYING SENTENCE BOUNDARIES
A MAXIMUM ENTROPY APPROACH TO IDENTIFYING SENTENCE BOUNDARIES
Authors: Jeffrey C. Reynar and Adwait Ratnaparkhi
Primarily assigned technology terms:
- algorithm
- decision tree
- decision-tree
- generalized iterative scaling
- identification
- iterative scaling
- maximum entropy
- maximum entropy approach
- maximum entropy framework
- maximum entropy model
- neural network
- pos tagging
- sentence detection
- sentence-boundary detection
- taggers
- tagging
- tiler
- training procedure
Other assigned terms:
- abbreviation
- alphabet
- annotated corpora
- annotated corpus
- approach
- brown corpus
- characters
- contextual information
- corpora
- decision rule
- distribution
- domain-specific information
- domain-specific knowledge
- entropy
- error rate
- feature
- genre
- joint probability
- joint probability distribution
- knowledge
- lexica
- lexicon
- likelihood
- part-of-speech
- part-of-speech tags
- penn treebank
- portability
- pos tag
- pos tag information
- probabilities
- probability
- probability distribution
- procedure
- punctuation
- punctuation marks
- roman alphabet
- sentence
- sentence boundaries
- sentence boundary
- sentences
- set size
- suffix
- symbol
- symbols
- system performance
- tag information
- tags
- test data
- test set
- text
- tokens
- training
- training corpus
- training data
- training data.
- tree
- treebank
- wall street journal text
- word
- words
- wsj corpus
