ACL RD-TEC 1.0 Summarization of C96-2192

Paper Title:
TAGGING SPOKEN LANGUAGE USING WRITTEN LANGUAGE STATISTICS

Authors: Joakim Nivre and Leif Gronqvist and Malin Gustafsson and TorbjSrn Lager and Sylvana Sofkova

Other assigned terms:

  • break
  • british national corpus
  • case
  • collocation
  • computational corpus
  • corpora
  • determiners
  • estimation
  • fact
  • grammatical structure
  • lexicon
  • likelihood
  • linguistics
  • markov models
  • method
  • nouns
  • orthography
  • part-of-speech
  • particles
  • parts of speech
  • parts-of-speech
  • passage
  • pause
  • pauses
  • phrase
  • prepositions
  • preprocessor
  • probabilities
  • probability
  • probability estimates
  • process
  • punctuation
  • punctuation marks
  • segments
  • spoken language
  • statistics
  • symbol
  • symbols
  • tagged corpus
  • tagset
  • terms
  • test corpus
  • text
  • tokens
  • training
  • training corpora
  • training corpus
  • training data
  • transcriptions
  • utterance
  • verb
  • word
  • word form
  • word types
  • words
  • written texts

Extracted Section Types:


This page last edited on 10 May 2017.

*** ***