Abstract
We present a novel method for higher-order dependency parsing which takes advantage of the general form of score functions written as arc-polynomials, a general framework which encompasses common higher-order score functions, and includes new ones. This method is based on non-linear optimization techniques, namely coordinate ascent and genetic search where we iteratively update a candidate parse. Updates are formulated as gradient-based operations, and are efficiently computed by auto-differentiation libraries. Experiments show that this method obtains results matching the recent state-of-the-art second order parsers on three standard datasets.- Anthology ID:
- 2022.aacl-main.85
- Volume:
- Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
- Month:
- November
- Year:
- 2022
- Address:
- Online only
- Editors:
- Yulan He, Heng Ji, Sujian Li, Yang Liu, Chua-Hui Chang
- Venues:
- AACL | IJCNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 1158–1171
- Language:
- URL:
- https://preview.aclanthology.org/remove-affiliations/2022.aacl-main.85/
- DOI:
- 10.18653/v1/2022.aacl-main.85
- Cite (ACL):
- Xudong Zhang, Joseph Le Roux, and Thierry Charnois. 2022. Higher-Order Dependency Parsing for Arc-Polynomial Score Functions via Gradient-Based Methods and Genetic Algorithm. In Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 1158–1171, Online only. Association for Computational Linguistics.
- Cite (Informal):
- Higher-Order Dependency Parsing for Arc-Polynomial Score Functions via Gradient-Based Methods and Genetic Algorithm (Zhang et al., AACL-IJCNLP 2022)
- PDF:
- https://preview.aclanthology.org/remove-affiliations/2022.aacl-main.85.pdf