Hierarchical Bracketing Encodings Work for Dependency Graphs
Not on the map. Why?
Abstract (arXiv)
We revisit hierarchical bracketing encodings from a practical perspective in the context of dependency graph parsing. The approach encodes graphs as sequences, enabling linear-time parsing with n tagging actions, and still representing reentrancies, cycles, and empty nodes. Compared to existing graph linearizations, this representation substantially reduces the label space while preserving structural information. We evaluate it on a multilingual and multi-formalism benchmark, showing competitive results and consistent improvements over other methods in exact match accuracy.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 15 of its 23 references that are in the map. First posted on arXiv 11 Sep 2025.
Builds on
15 of 23 references.
References · 15
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
- 2019Unsupervised Cross-lingual Representation Learning at Scalecited by 3,935
- 2019XLNet: Generalized Autoregressive Pretraining for Language Understandingcited by 2,811
- 2015Empirical Evaluation of Rectified Activations in Convolutional Networkcited by 519
- 2016End-to-end Sequence Labeling via Bi-directional LSTM-CNNs-CRFcited by 341
- 2018Simpler but More Accurate Semantic Dependency Parsingcited by 46
- 2019Viable Dependency Parsing as Sequence Labelingcited by 34
- 2018Constituent Parsing as Sequence Labelingcited by 26
- 2019Second-Order Semantic Dependency Parsing with End-to-End Neural Networkscited by 21
- 2019Tetra-Tagging: Word-Synchronous Parsing with Linear-Time Inferencecited by 17
- 2020Transition-based Semantic Dependency Parsing with Pointer Networkscited by 16
- 2020Discontinuous Constituent Parsing as Sequence Labelingcited by 9
3 more
Built on by
Not cited yet.