学来的语法主干不比规则主干更能提升分句精度。
Better heads do not guarantee better binarized constituency parsing
- 用模型学习主干结构替代规则，提升内在头预测能力
- 虽在CTB数据集上略有整体提升，但标点敏感指标下降
- 跨语料库迁移时性能更不稳定，凸显语言合理性非最优
我们重新审视了带标点感知的句法树二叉化方法，探究依赖诱导的主干结构是否能改善二叉化解析器的监督效果。尽管学习得到的主干在内在头预测任务中显著优于规则方法，但在去二叉化后并未带来稳定解析性能提升。特别是在标点敏感的宏平均F1指标上，学习主干表现反而劣于规则二叉化，尽管在CTB数据集上整体略有增益。跨语料库迁移中也出现类似不稳定性。结果表明，语言学上合理的主干结构并不一定在作为二叉化控制信号时最优。本文呈现了一个负向结论：更好的头预测并不意味着更好的标点敏感句法解析。
原文摘要 · Abstract (English)
We revisit punctuation-aware tree binarization for constituency parsing and ask whether dependency-induced headedness improves binary parser supervision. Although learned heads substantially outperform rule-based heads in intrinsic head prediction, they do not yield consistent parsing gains after debinarization. In particular, punctuation-conditioned evaluation shows that learned headedness underperforms rule-based binarization in macro-average punctuation-sensitive $F_1$, despite a small overall gain on CTB. Similar instability appears under cross-treebank transfer. These results suggest that \ycc{linguistically grounded} headedness is not necessarily parser-optimal when used as a binarization control signal. The paper presents a negative result: better head prediction does not imply better punctuation-sensitive constituency parsing.
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。