Use this link to cite:
https://hdl.handle.net/2183/45744 Hierarchical Bracketing Encodings for Dependency Parsing as Tagging
Loading...
Identifiers
Publication date
Authors
Advisors
Other responsabilities
Journal Title
Bibliographic citation
Ana Ezquerro, David Vilares, Anssi Yli-Jyrä, and Carlos Gómez-Rodríguez. 2025. Hierarchical Bracketing Encodings for Dependency Parsing as Tagging. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 18436–18450, Vienna, Austria. Association for Computational Linguistics. DOI: 10.18653/v1/2025.acl-long.903
Type of academic work
Academic degree
Abstract
[Abstract]: We present a family of encodings for sequence labeling dependency parsing, based on the concept of hierarchical bracketing. We show that the existing 4-bit projective encoding belongs to this family, but it is suboptimal in the number of labels used to encode a tree. We derive an optimal hierarchical bracketing, which minimizes the number of symbols used and encodes projective trees using only 12 distinct labels (vs. 16 for the 4-bit encoding). We also extend optimal hierarchical bracketing to support arbitrary non-projectivity in a more compact way than previous encodings. Our new encodings yield competitive accuracy on a diverse set of treebanks.
Description
Presented at the 63rd Annual Meeting of the Association for Computational Linguistics, July 2025, Vienna, Austria.
Keywords
Editor version
Rights
Attribution 4.0 International
Collections
Except where otherwise noted, this item's license is described as Attribution 4.0 International