A Dynamic Oracle for Linear-Time 2-Planar Dependency Parsing
Computation and Language
2018-05-17 v2
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.
Keywords
Cite
@article{arxiv.1805.05202,
title = {A Dynamic Oracle for Linear-Time 2-Planar Dependency Parsing},
author = {Daniel Fernández-González and Carlos Gómez-Rodríguez},
journal= {arXiv preprint arXiv:1805.05202},
year = {2018}
}
Comments
Proceedings of NAACL-HLT 2018. 7 pages