We present a novel transition system, based on the Covington non-projective parser, introducing non-local transitions that can directly create arcs involving nodes to the left of the current focus positions. This avoids the need for long sequences of No-Arc transitions to create long-distance arcs, thus alleviating error propagation. The resulting parser outperforms the original version and achieves the best accuracy on the Stanford Dependencies conversion of the Penn Treebank among greedy transition-based algorithms.
Cite
@article{arxiv.1710.09340,
title = {Non-Projective Dependency Parsing with Non-Local Transitions},
author = {Daniel Fernández-González and Carlos Gómez-Rodríguez},
journal= {arXiv preprint arXiv:1710.09340},
year = {2018}
}