Abstract
Dynamic oracles provide strong supervision for training constituency parsers with exploration, but must be custom defined for a given parser’s transition system. We explore using a policy gradient method as a parser-agnostic alternative. In addition to directly optimizing for a tree-level metric such as F1, policy gradient has the potential to reduce exposure bias by allowing exploration during training; moreover, it does not require a dynamic oracle for supervision. On four constituency parsers in three languages, the method substantially outperforms static oracle likelihood training in almost all settings. For parsers where a dynamic oracle is available (including a novel oracle which we define for the transition system of Dyer et al., 2016), policy gradient typically recaptures a substantial fraction of the performance gain afforded by the dynamic oracle.- Anthology ID:
- P18-2075
- Volume:
- Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
- Month:
- July
- Year:
- 2018
- Address:
- Melbourne, Australia
- Editors:
- Iryna Gurevych, Yusuke Miyao
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 469–476
- Language:
- URL:
- https://aclanthology.org/P18-2075
- DOI:
- 10.18653/v1/P18-2075
- Cite (ACL):
- Daniel Fried and Dan Klein. 2018. Policy Gradient as a Proxy for Dynamic Oracles in Constituency Parsing. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 469–476, Melbourne, Australia. Association for Computational Linguistics.
- Cite (Informal):
- Policy Gradient as a Proxy for Dynamic Oracles in Constituency Parsing (Fried & Klein, ACL 2018)
- PDF:
- https://preview.aclanthology.org/improve-issue-templates/P18-2075.pdf