A Tabular Method for Dynamic Oracles in Transition-Based Parsing

Yoav Goldberg, Francesco Sartorio, Giorgio Satta


Abstract
We develop parsing oracles for two transition-based dependency parsers, including the arc-standard parser, solving a problem that was left open in (Goldberg and Nivre, 2013). We experimentally show that using these oracles during training yields superior parsing accuracies on many languages.
Anthology ID:
Q14-1010
Volume:
Transactions of the Association for Computational Linguistics, Volume 2
Month:
Year:
2014
Address:
Cambridge, MA
Editors:
Dekang Lin, Michael Collins, Lillian Lee
Venue:
TACL
SIG:
Publisher:
MIT Press
Note:
Pages:
119–130
Language:
URL:
https://aclanthology.org/Q14-1010
DOI:
10.1162/tacl_a_00170
Bibkey:
Cite (ACL):
Yoav Goldberg, Francesco Sartorio, and Giorgio Satta. 2014. A Tabular Method for Dynamic Oracles in Transition-Based Parsing. Transactions of the Association for Computational Linguistics, 2:119–130.
Cite (Informal):
A Tabular Method for Dynamic Oracles in Transition-Based Parsing (Goldberg et al., TACL 2014)
Copy Citation:
PDF:
https://aclanthology.org/Q14-1010.pdf
Video:
 https://aclanthology.org/Q14-1010.mp4
Data
Penn Treebank