ACL 2025long0 citations
Hierarchical Bracketing Encodings for Dependency Parsing as Tagging
Ana Ezquerro, David Vilares, Anssi Yli-Jyrä, Carlos Gómez-Rodríguez
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.
BibTeX
@inproceedings{ezquerro-etal-2025-hierarchical,
title = "Hierarchical Bracketing Encodings for Dependency Parsing as Tagging",
author = {Ezquerro, Ana and
Vilares, David and
Yli-Jyr{\"a}, Anssi and
G{\'o}mez-Rodr{\'i}guez, Carlos},
editor = "Che, Wanxiang and
Nabende, Joyce and
Shutova, Ekaterina and
Pilehvar, Mohammad Taher",
booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.acl-long.903/",
doi = "10.18653/v1/2025.acl-long.903",
pages = "18436--18450",
ISBN = "979-8-89176-251-0"
}