Dynamic Oracles for Top-Down and In-Order Shift-Reduce Constituent Parsing

Daniel Fernández-González, Carlos Gómez-Rodríguez


Abstract
We introduce novel dynamic oracles for training two of the most accurate known shift-reduce algorithms for constituent parsing: the top-down and in-order transition-based parsers. In both cases, the dynamic oracles manage to notably increase their accuracy, in comparison to that obtained by performing classic static training. In addition, by improving the performance of the state-of-the-art in-order shift-reduce parser, we achieve the best accuracy to date (92.0 F1) obtained by a fully-supervised single-model greedy shift-reduce constituent parser on the WSJ benchmark.
Anthology ID:
D18-1161
Volume:
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
Month:
October-November
Year:
2018
Address:
Brussels, Belgium
Editors:
Ellen Riloff, David Chiang, Julia Hockenmaier, Jun’ichi Tsujii
Venue:
EMNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
1303–1313
Language:
URL:
https://aclanthology.org/D18-1161
DOI:
10.18653/v1/D18-1161
Bibkey:
Cite (ACL):
Daniel Fernández-González and Carlos Gómez-Rodríguez. 2018. Dynamic Oracles for Top-Down and In-Order Shift-Reduce Constituent Parsing. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 1303–1313, Brussels, Belgium. Association for Computational Linguistics.
Cite (Informal):
Dynamic Oracles for Top-Down and In-Order Shift-Reduce Constituent Parsing (Fernández-González & Gómez-Rodríguez, EMNLP 2018)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-3/D18-1161.pdf
Video:
 https://preview.aclanthology.org/nschneid-patch-3/D18-1161.mp4
Code
 danifg/Dynamic-InOrderParser
Data
Penn Treebank