Instance-based natural language generation

  title={Instance-based natural language generation},
  author={S SVARGE and H CMELLIS},
  • S V A R G E S, C M E L L I S H
  • Published 2010
We investigate the use of instance-based ranking methods for surface realization in natural language generation. Our approach to instance-based natural language generation (IBNLG) employs two components: a rule system that ‘overgenerates’ a number of realization candidates from a meaning representation and an instance-based ranker that scores the candidates according to their similarity to examples taken from a training corpus. We develop an efficient search technique for identifying the… CONTINUE READING

Similar Papers