Hierarchical Bracketing Encodings for Dependency Parsing as Tagging
Ezquerro, Ana, Vilares, David, Yli-Jyrä, Anssi, Gómez-Rodríguez, Carlos
–arXiv.org Artificial Intelligence
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.
arXiv.org Artificial Intelligence
Jul-11-2025
- Country:
- Asia > Singapore (0.04)
- Europe
- Czechia > Prague (0.04)
- Finland
- France > Provence-Alpes-Côte d'Azur
- Bouches-du-Rhône > Marseille (0.04)
- Germany > Saxony
- Dresden (0.04)
- Italy > Trentino-Alto Adige/Südtirol
- Trentino Province > Trento (0.04)
- Spain > Catalonia
- Barcelona Province > Barcelona (0.04)
- North America
- Canada > Ontario
- Toronto (0.04)
- United States
- Michigan > Washtenaw County
- Ann Arbor (0.04)
- Minnesota > Hennepin County
- Minneapolis (0.14)
- Michigan > Washtenaw County
- Canada > Ontario
- Genre:
- Research Report (0.81)
- Technology: