用分层括号编码改进依存句法分析，标签更少效果更好。
Hierarchical Bracketing Encodings for Dependency Parsing as Tagging
- 基于分层括号思想设计新标签编码方式
- 仅用12个标签即可表示投射树，比旧方法少4个
- 支持非投射结构且编码更紧凑，适合多语言研究
我们提出一类基于分层括号思想的序列标注依存句法分析编码方法。证明现有的4比特投射编码属于此类，但标签数量并非最优。我们推导出一种最优分层括号编码，将投射树的标签数降至12个（原4比特编码为16个）。同时将该编码扩展至任意非投射情况，相比先前方法更为紧凑。新编码在多种语料库上表现良好，准确率具有竞争力。
原文摘要 · Abstract (English)
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.
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。