Non-Projective Dependency Parsing with Non-Local Transitions

Daniel Fernández-González, Carlos Gómez-Rodríguez


Abstract
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-Arcs 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 parsers.
Anthology ID:
N18-2109
Volume:
Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers)
Month:
June
Year:
2018
Address:
New Orleans, Louisiana
Editors:
Marilyn Walker, Heng Ji, Amanda Stent
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
693–700
Language:
URL:
https://aclanthology.org/N18-2109
DOI:
10.18653/v1/N18-2109
Bibkey:
Cite (ACL):
Daniel Fernández-González and Carlos Gómez-Rodríguez. 2018. Non-Projective Dependency Parsing with Non-Local Transitions. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers), pages 693–700, New Orleans, Louisiana. Association for Computational Linguistics.
Cite (Informal):
Non-Projective Dependency Parsing with Non-Local Transitions (Fernández-González & Gómez-Rodríguez, NAACL 2018)
Copy Citation:
PDF:
https://aclanthology.org/N18-2109.pdf
Video:
 https://aclanthology.org/N18-2109.mp4