用分层括号编码让依存句法分析更快更准
Hierarchical Bracketing Encodings Work for Dependency Graphs
- 将语法图转为序列，用括号结构表示复杂语法关系
- 标签空间大幅缩小，准确率超越现有方法
- 适合需要高效解析的多语言语法研究
我们从实用角度重新审视了分层括号编码在依存图解析中的应用。该方法将图结构编码为序列，实现线性时间解析，仅需 $n$ 次标记操作，同时保留重叠、环路和空节点等复杂结构。相比现有图线性化方法，该表示显著压缩标签空间，同时保持完整结构信息。我们在多语言、多形式体系的基准上进行评估，结果具有竞争力，且在精确匹配准确率上持续优于其他方法。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。