arXiv cs.CL· Muhammad Azam Afridi, Rajab Ali, Marco Passarotti·· 12 小时前AI 评分24
POS-Signature 演示检索用于上下文依存句法分析
POS-Signature Demonstration Retrieval for In-Context Dependency Parsing
AI 导读
研究提出用加权词性统计的 POS-signature 策略为 Universal Dependencies 依存句法分析挑选演示样本，从标注训练集检索三个长度兼容的 gold 解析例句。
正文 · 原文
Abstract:Demonstrations for in-context learning are often retrieved by semantic similarity, which may be a poor proxy for relevance in structured prediction. We study demonstration selection for Universal Dependencies parsing with a POS-signature policy that represents sentences with weighted part-of-speech statistics and retrieves three length-compatible, gold-parsed examples from the labeled training split. We evaluate two open-weight language models without fine-tuning on all 2,077 sentences of the UD English Web Treebank test set, comparing the policy with shot- and format-matched fixed and semantic three-shot baselines, as well as zero-shot, chain-of-thought, and critique-refinement systems. POS-signature retrieval yields the highest labeled attachment score among the tested prompting systems for both models (72.4 and 73.2), outperforming semantic retrieval by 1.9 and 2.7 points; paired-bootstrap 95% confidence intervals exclude zero for both contrasts. Chain-of-thought and refinement comparisons vary across models. These exploratory results favor the tested POS-signature retrieval approach on English-EWT. We release the prompts, archived outputs, and evaluation code.
| Comments: | 14 pages, 1 figure, 8 tables. Code and research artifacts: this https URL |
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2610.31966 [cs.CL] |
| (or arXiv:2610.31966v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.31966 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Muhammad Azam Afridi [view email]
[v1]
Thu, 22 Oct 2026 22:15:48 UTC (108 KB)
来源：arXiv cs.CL · arxiv.org