Hierarchical Bracketing Encodings for Dependency Parsing as Tagging
Ana Ezquerro, David Vilares, Anssi Yli-Jyrä, Carlos Gómez-Rodríguez
摘要
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.
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了每一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
它引用的顶会 Paper1
相关 Paper
- Headed-Span-Based Projective Dependency ParsingSonglin Yang, Kewei TuACL 2022 · 被引用 16 次
- Dependency Graph Parsing as Sequence LabelingAna Ezquerro, David Vilares, Carlos Gómez-RodríguezEMNLP 2024 · 被引用 1 次
- Discontinuous Constituent Parsing as Sequence LabelingDavid Vilares, Carlos Gómez-RodríguezEMNLP 2020 · 被引用 1 次
- Semantic Role Labeling as Syntactic Dependency ParsingTianze Shi, Igor Malioutov, Ozan IrsoyEMNLP 2020 · 被引用 15 次
- Learned Incremental Representations for ParsingNikita Kitaev, Thomas Lu, Dan KleinACL 2022
