Probabilistic Models of Short and Long Distance Word Dependencies in Running Text.
Julian KupiecPublished in: HLT (1) (1989)
Keyphrases
- long distance
- probabilistic model
- mutual exclusion
- keywords
- english text
- dependency relations
- word pairs
- sentence level
- text input
- graphical models
- linguistic information
- text corpus
- text retrieval
- string matching
- multiword
- related words
- natural language text
- co occurrence
- syntactic categories
- text documents
- noun phrases
- lexical features
- printed documents
- english words
- text segments
- conditional random fields
- word counts
- information retrieval
- concept space
- word level
- text mining
- chinese text
- page layout
- named entity recognizer
- punctuation marks
- word recognition
- hidden variables
- n gram
- generative model
- expectation maximization
- language model
- bayesian networks
- document analysis
- semantic information