Vine pruning for efficient multi-pass dependency parsing

  • Authors:
  • Alexander M. Rush;Slav Petrov

  • Affiliations:
  • MIT CSAIL, Cambridge, MA;Google, New York, NY

  • Venue:
  • NAACL HLT '12 Proceedings of the 2012 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
  • Year:
  • 2012

Quantified Score

Hi-index 0.00

Visualization

Abstract

Coarse-to-fine inference has been shown to be a robust approximate method for improving the efficiency of structured prediction models while preserving their accuracy. We propose a multi-pass coarse-to-fine architecture for dependency parsing using linear-time vine pruning and structured prediction cascades. Our first-, second-, and third-order models achieve accuracies comparable to those of their unpruned counterparts, while exploring only a fraction of the search space. We observe speed-ups of up to two orders of magnitude compared to exhaustive search. Our pruned third-order model is twice as fast as an unpruned first-order model and also compares favorably to a state-of-the-art transition-based parser for multiple languages.