Non-projective Dependency Parsing using Spanning Tree Algorithms

4.1 Results

1. How did MST parsing compare with projective parsers on Czech?
   On the full PDT, accuracy (words with correct parent) was 84.1% for single-best and 84.4% for factored MIRA, vs 83.3% for the projective Eisner-based parser, 82.8% for Collins et al. (1999) and 80.0% for Nivre and Nilsson’s pseudo-projective parser. On non-projective sentences, 81.0–81.5% vs 74.8%.
   • McDonald et al., 2005, Non-projective Dependency Parsing using Spanning Tree Algorithms (Proceedings of Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing (HLT/EMNLP 2005)), §4.1, pp. 528–529
2. Does searching all non-projective trees hurt on mostly projective Czech, and on fully projective English?
   Not on Czech: the weights are learned with respect to the parsing algorithm and disfavour unlikely non-projective edges. On projective English (Penn Treebank), Chu-Liu-Edmonds was slightly worse (90.2% vs 90.9%), since Eisner exploits the prior knowledge that all trees are projective.
   • McDonald et al., 2005, Non-projective Dependency Parsing using Spanning Tree Algorithms (Proceedings of Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing (HLT/EMNLP 2005)), §4.1, pp. 528–529