Sequential Graph Dependency Parser

Sean Welleck, Kyunghyun Cho


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.
Anthology ID:
R19-1153
Volume:
Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2019)
Month:
September
Year:
2019
Address:
Varna, Bulgaria
Editors:
Ruslan Mitkov, Galia Angelova
Venue:
RANLP
SIG:
Publisher:
INCOMA Ltd.
Note:
Pages:
1338–1345
Language:
URL:
https://aclanthology.org/R19-1153
DOI:
10.26615/978-954-452-056-4_153
Bibkey:
Cite (ACL):
Sean Welleck and Kyunghyun Cho. 2019. Sequential Graph Dependency Parser. In Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2019), pages 1338–1345, Varna, Bulgaria. INCOMA Ltd..
Cite (Informal):
Sequential Graph Dependency Parser (Welleck & Cho, RANLP 2019)
Copy Citation:
PDF:
https://aclanthology.org/R19-1153.pdf