Dependency-based n-gram models for general purpose sentence realisation

  • Authors:
  • Yuqing Guo;Josef van Genabith;Haifeng Wang

  • Affiliations:
  • Dublin City University, Dublin, Ireland;Dublin City University, Dublin, Ireland;Toshiba (China) Research & Development Center, Beijing, China

  • Venue:
  • COLING '08 Proceedings of the 22nd International Conference on Computational Linguistics - Volume 1
  • Year:
  • 2008

Quantified Score

Hi-index 0.00

Visualization

Abstract

We present dependency-based n-gram models for general-purpose, wide-coverage, probabilistic sentence realisation. Our method linearises unordered dependencies in input representations directly rather than via the application of grammar rules, as in traditional chart-based generators. The method is simple, efficient, and achieves competitive accuracy and complete coverage on standard English (Penn-II, 0.7440 BLEU, 0.05 sec/sent) and Chinese (CTB6, 0.7123 BLEU, 0.14 sec/sent) test data.