保留标点信息提升依存句法分析准确率
Punctuation-aware treebank tree binarization
- 标点作为兄弟节点保留在分词前，避免结构失真
- 在Penn Treebank上头-子关系预测准确率达91.85%
- 适合需要高精度句法分析的研究者使用
本文提出一种保留标点的树库二叉化资源与评估套件。标准二叉化流程在选择中心词前丢弃标点，改变成分结构并损害头-子识别。我们发布：(1) 可复现的预处理管道，将标点作为兄弟节点保留至二叉化前；(2) 衍生产物与元数据（中间@X标记、可逆性签名、对齐索引）；(3) 包含头-子预测、往返可逆性及与衍生资源（CCGbank）结构兼容性的评估套件。在Penn Treebank上，该方法使头预测准确率从73.66%（Collins规则）和86.66%（MLP）提升至91.85%（相同分类器），且对齐效果媲美CCGbank。所有代码、配置文件与文档均已公开，支持复制与扩展至其他语料库。
原文摘要 · Abstract (English)
This article presents a curated resource and evaluation suite for punctuation-aware treebank binarization. Standard binarization pipelines drop punctuation before head selection, which alters constituent shape and harms head-child identification. We release (1) a reproducible pipeline that preserves punctuation as sibling nodes prior to binarization, (2) derived artifacts and metadata (intermediate @X markers, reversibility signatures, alignment indices), and (3) an accompanying evaluation suite covering head-child prediction, round-trip reversibility, and structural compatibility with derivational resources (CCGbank). On the Penn Treebank, punctuation-aware preprocessing improves head prediction accuracy from 73.66\% (Collins rules) and 86.66\% (MLP) to 91.85\% with the same classifier, and achieves competitive alignment against CCGbank derivations. All code, configuration files, and documentation are released to enable replication and extension to other corpora.
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。