vix.ing · top · new · best · stats

Hierarchical Bracketing Encodings for Dependency Parsing as Tagging

2025/05/16 by Ana Ezquerro, David Vilares, Ezquerro, Ana +5 · 1 citation
Computer Science · #Algorithms and Data Compression #Bracketing (phenomenology) #Computation and Language (cs.CL) #Dependency (UML) #ENCODE #Encoding (memory) #FOS: Computer and information sciences #Natural Language Processing Techniques #Parsing #Projective test #Sequence (biology) #Set (abstract data type) #semigroups and automata theory

paper · pdf · doi:10.48550/arxiv.2505.11693

published in arXiv (Cornell University) (Cornell University)

openalex publication_date 2025/05/16 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05

Abstract

We present a family of encodings for sequence labeling dependency parsing, based on the concept of hierarchical bracketing. We prove 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.

Citations

Cited by

Related