Abstract
We introduce a novel dependency parser, the hexatagger, that constructs dependency trees by tagging the words in a sentence with elements from a finite set of possible tags. In contrast to many approaches to dependency parsing, our approach is fully parallelizable at training time, i.e., the structure-building actions needed to build a dependency parse can be predicted in parallel to each other. Additionally, exact decoding is linear in time and space complexity. Furthermore, we derive a probabilistic dependency parser that predicts hexatags using no more than a linear model with features from a pretrained language model, i.e., we forsake a bespoke architecture explicitly designed for the task. Despite the generality and simplicity of our approach, we achieve state-of-the-art performance of 96.4 LAS and 97.4 UAS on the Penn Treebank test set. Additionally, our parser’s linear time complexity and parallelism significantly improve computational efficiency, with a roughly 10-times speed-up over previous state-of-the-art models during decoding.- Anthology ID:
- 2023.acl-short.124
- Volume:
- Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
- Month:
- July
- Year:
- 2023
- Address:
- Toronto, Canada
- Editors:
- Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 1453–1464
- Language:
- URL:
- https://aclanthology.org/2023.acl-short.124
- DOI:
- 10.18653/v1/2023.acl-short.124
- Award:
- Outstanding Paper Award
- Cite (ACL):
- Afra Amini, Tianyu Liu, and Ryan Cotterell. 2023. Hexatagging: Projective Dependency Parsing as Tagging. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 1453–1464, Toronto, Canada. Association for Computational Linguistics.
- Cite (Informal):
- Hexatagging: Projective Dependency Parsing as Tagging (Amini et al., ACL 2023)
- PDF:
- https://preview.aclanthology.org/improve-issue-templates/2023.acl-short.124.pdf