A Minimal Span-Based Neural Constituency Parser

Mitchell Stern, Jacob Andreas, Dan Klein


Abstract
In this work, we present a minimal neural model for constituency parsing based on independent scoring of labels and spans. We show that this model is not only compatible with classical dynamic programming techniques, but also admits a novel greedy top-down inference algorithm based on recursive partitioning of the input. We demonstrate empirically that both prediction schemes are competitive with recent work, and when combined with basic extensions to the scoring model are capable of achieving state-of-the-art single-model performance on the Penn Treebank (91.79 F1) and strong performance on the French Treebank (82.23 F1).
Anthology ID:
P17-1076
Volume:
Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
July
Year:
2017
Address:
Vancouver, Canada
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
818–827
Language:
URL:
https://aclanthology.org/P17-1076
DOI:
10.18653/v1/P17-1076
Bibkey:
Cite (ACL):
Mitchell Stern, Jacob Andreas, and Dan Klein. 2017. A Minimal Span-Based Neural Constituency Parser. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 818–827, Vancouver, Canada. Association for Computational Linguistics.
Cite (Informal):
A Minimal Span-Based Neural Constituency Parser (Stern et al., ACL 2017)
Copy Citation:
PDF:
https://aclanthology.org/P17-1076.pdf
Video:
 https://vimeo.com/234957467
Data
Penn Treebank