Tackling Error Propagation through Reinforcement Learning: A Case of Greedy Dependency Parsing

Minh Lê, Antske Fokkens


Abstract
Error propagation is a common problem in NLP. Reinforcement learning explores erroneous states during training and can therefore be more robust when mistakes are made early in a process. In this paper, we apply reinforcement learning to greedy dependency parsing which is known to suffer from error propagation. Reinforcement learning improves accuracy of both labeled and unlabeled dependencies of the Stanford Neural Dependency Parser, a high performance greedy parser, while maintaining its efficiency. We investigate the portion of errors which are the result of error propagation and confirm that reinforcement learning reduces the occurrence of error propagation.
Anthology ID:
E17-1064
Volume:
Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long 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:
677–687
Language:
URL:
https://aclanthology.org/E17-1064
DOI:
Bibkey:
Cite (ACL):
Minh Lê and Antske Fokkens. 2017. Tackling Error Propagation through Reinforcement Learning: A Case of Greedy Dependency Parsing. In Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers, pages 677–687, Valencia, Spain. Association for Computational Linguistics.
Cite (Informal):
Tackling Error Propagation through Reinforcement Learning: A Case of Greedy Dependency Parsing (Lê & Fokkens, EACL 2017)
Copy Citation:
PDF:
https://aclanthology.org/E17-1064.pdf
Code
 cltl/redep-java