{"ID":2872189,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.09388","arxiv_id":"2509.09388","title":"Hierarchical Bracketing Encodings Work for Dependency Graphs","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.","short_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,...","url_abs":"https://arxiv.org/abs/2509.09388","url_pdf":"https://arxiv.org/pdf/2509.09388v1","authors":"[\"Ana Ezquerro\",\"Carlos Gómez-Rodríguez\",\"David Vilares\"]","published":"2025-09-11T12:08:22Z","proceeding":"cs.CL","tasks":"[\"cs.CL\"]","methods":"[]","has_code":false}