Don’t Stop Me Now! Using Global Dynamic Oracles to Correct Training Biases of Transition-Based Dependency Parsers

Lauriane Aufrant, Guillaume Wisniewski, François Yvon


Abstract
This paper formalizes a sound extension of dynamic oracles to global training, in the frame of transition-based dependency parsers. By dispensing with the pre-computation of references, this extension widens the training strategies that can be entertained for such parsers; we show this by revisiting two standard training procedures, early-update and max-violation, to correct some of their search space sampling biases. Experimentally, on the SPMRL treebanks, this improvement increases the similarity between the train and test distributions and yields performance improvements up to 0.7 UAS, without any computation overhead.
Anthology ID:
E17-2051
Volume:
Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers
Month:
April
Year:
2017
Address:
Valencia, Spain
Editors:
Mirella Lapata, Phil Blunsom, Alexander Koller
Venue:
EACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
318–323
Language:
URL:
https://aclanthology.org/E17-2051
DOI:
Bibkey:
Cite (ACL):
Lauriane Aufrant, Guillaume Wisniewski, and François Yvon. 2017. Don’t Stop Me Now! Using Global Dynamic Oracles to Correct Training Biases of Transition-Based Dependency Parsers. In Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers, pages 318–323, Valencia, Spain. Association for Computational Linguistics.
Cite (Informal):
Don’t Stop Me Now! Using Global Dynamic Oracles to Correct Training Biases of Transition-Based Dependency Parsers (Aufrant et al., EACL 2017)
Copy Citation:
PDF:
https://aclanthology.org/E17-2051.pdf