From Dyna
Jump to: navigation, search

In this paper (reference below) we described the performance of a dependency parsing system written partly in Dyna. The algorithms used in that paper are given in Dyna here; the C++ code that the current Dyna compiler produces is here.

This parser and labeler formed part of our entry in the 2006 CoNLL shared task. It didn't perform very competitively, largely because it was designed for speed and precision of dependency links (not recall). These Dyna programs might be helpful examples, nonetheless.

  • [1] Dreyer, Markus, David A. Smith, and Noah A. Smith (2006). Vine Parsing and Minimum Risk Reranking for Speed and Precision. Proceedings of the Conference on Natural Language Learning (CoNLL), New York, June.
  • [2] Eisner, Jason, and Noah A. Smith (2005). Parsing with soft and hard constraints on dependency length. Proceedings of the International Workshop on Parsing Technologies (IWPT), Vancouver, October.
Personal tools