A decoder for probabilistic synchronous tree insertion grammars

  • Authors:
  • Steve DeNeefe;Kevin Knight;Heiko Vogler

  • Affiliations:
  • USC Information Sciences Institute, Marina del Rey, CA;USC Information Sciences Institute, Marina del Rey, CA;Technische Universität Dresden, Dresden

  • Venue:
  • ATANLP '10 Proceedings of the 2010 Workshop on Applications of Tree Automata in Natural Language Processing
  • Year:
  • 2010

Quantified Score

Hi-index 0.00

Visualization

Abstract

Synchronous tree insertion grammars (STIG) are formal models for syntax-based machine translation. We formalize a decoder for probabilistic STIG; the decoder transforms every source-language string into a target-language tree and calculates the probability of this transformation.