Vine Pruning for Efficient Multi-Pass Dependency Parsing

  title={Vine Pruning for Efficient Multi-Pass Dependency Parsing},
  author={Alexander M. Rush and Slav Petrov},
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… CONTINUE READING
Highly Cited
This paper has 60 citations. REVIEW CITATIONS
44 Citations
35 References
Similar Papers

Similar Papers

Loading similar papers…