Dynamic programming for linear-time incremental parsing

  • Authors:
  • Liang Huang;Kenji Sagae

  • Affiliations:
  • USC Information Sciences Institute, Marina del Rey, CA;USC Institute for Creative Technologies, Marina del Rey, CA

  • Venue:
  • ACL '10 Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics
  • Year:
  • 2010

Quantified Score

Hi-index 0.00

Visualization

Abstract

Incremental parsing techniques such as shift-reduce have gained popularity thanks to their efficiency, but there remains a major problem: the search is greedy and only explores a tiny fraction of the whole space (even with beam search) as opposed to dynamic programming. We show that, surprisingly, dynamic programming is in fact possible for many shift-reduce parsers, by merging "equivalent" stacks based on feature values. Empirically, our algorithm yields up to a five-fold speedup over a state-of-the-art shift-reduce dependency parser with no loss in accuracy. Better search also leads to better learning, and our final parser outperforms all previously reported dependency parsers for English and Chinese, yet is much faster.