English

Sequential Graph Dependency Parser

Machine Learning 2019-10-25 v2 Computation and Language Machine Learning

Abstract

We propose a method for non-projective dependency parsing by incrementally predicting a set of edges. Since the edges do not have a pre-specified order, we propose a set-based learning method. Our method blends graph, transition, and easy-first parsing, including a prior state of the parser as a special case. The proposed transition-based method successfully parses near the state of the art on both projective and non-projective languages, without assuming a certain parsing order.

Keywords

Cite

@article{arxiv.1905.10930,
  title  = {Sequential Graph Dependency Parser},
  author = {Sean Welleck and Kyunghyun Cho},
  journal= {arXiv preprint arXiv:1905.10930},
  year   = {2019}
}

Comments

RANLP 2019