A Dynamic Oracle for Linear-Time 2-Planar Dependency Parsing

Daniel Fernández-González, Carlos Gómez-Rodríguez


Abstract
We propose an efficient dynamic oracle for training the 2-Planar transition-based parser, a linear-time parser with over 99% coverage on non-projective syntactic corpora. This novel approach outperforms the static training strategy in the vast majority of languages tested and scored better on most datasets than the arc-hybrid parser enhanced with the Swap transition, which can handle unrestricted non-projectivity.
Anthology ID:
N18-2062
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:
386–392
Language:
URL:
https://aclanthology.org/N18-2062
DOI:
10.18653/v1/N18-2062
Bibkey:
Cite (ACL):
Daniel Fernández-González and Carlos Gómez-Rodríguez. 2018. A Dynamic Oracle for Linear-Time 2-Planar Dependency Parsing. 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 386–392, New Orleans, Louisiana. Association for Computational Linguistics.
Cite (Informal):
A Dynamic Oracle for Linear-Time 2-Planar Dependency Parsing (Fernández-González & Gómez-Rodríguez, NAACL 2018)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-1/N18-2062.pdf