Treating 'free word order' in machine translation

  • Authors:
  • Ralf Steinberger

  • Affiliations:
  • UMIST - Centre for Computational Linguistics, Manchester, UK

  • Venue:
  • COLING '94 Proceedings of the 15th conference on Computational linguistics - Volume 1
  • Year:
  • 1994

Quantified Score

Hi-index 0.00

Visualization

Abstract

In free word order languages, every sentence is embedded in its specific context. The order of constituents is determined by the categories theme, rheme and contraslive focus. This paper shows how to recognise and to translate these categories automatically on a sentential basis, so that sentence embedding can be achieved without having to refer to the context. Traditionally neglected modifier classes are fully covered by the proposed method.