Hierarchical Bracketing Encodings Work for Dependency Graphs

2025-09-11

AI Summary

Existing linearization methods for dependency graph parsing suffer from excessively large label spaces and fail to preserve complex structural phenomena—including re-entrant edges, cycles, and null nodes. To address this, we propose a novel graph-to-sequence paradigm based on hierarchical bracket encoding, which recursively represents dependency graphs as nested bracket sequences. This approach requires only a constant-size label set (O(1)), enables linear-time parsing, and fully retains both topological and hierarchical graph structure. Unlike conventional action-sequence or flattened encodings, our method leverages hierarchical syntactic grammar to guide structure-aware representation learning. We conduct systematic evaluation across multilingual and multi-formalism benchmarks (UD, DM, PSD), demonstrating significantly higher exact-match accuracy than state-of-the-art linearization methods. Our framework offers a more concise, robust, and scalable modeling paradigm for graph-structured parsing.

Technology Category

• Natural Language Processing: Syntax — Tagging, Chunking & Parsing
• Machine Learning: Graph-based Machine Learning
• Reasoning under Uncertainty: Graphical Models

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

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.

Problem

• Linear-time dependency graph parsing
• Reducing label space for graph linearizations
• Handling reentrancies, cycles, and empty nodes

Innovation

• Hierarchical bracketing encodes dependency graphs
• Linear-time parsing with n tagging actions
• Reduces label space preserving structural information