arXiv cs.CL· Aayush Acharya, Qi Zhang, Eduard Dragut, Longin Jan Latecki·· 12 小时前AI 评分31
本体引导的知识图谱构建：从结构化元数据与气候科学论文中提取知识
Ontology-Guided Knowledge Graph Construction from Structured Metadata and Climate Science Publications
AI 导读
研究团队提出一个智能体式、本体引导的知识图谱构建框架，由专门智能体分别负责文档理解、信息抽取、本体一致性与实体链接。在 1000 条三元组的一致性研究中，Gemini-2.5-flash 与三位人工标注者的 Cohen's κ 为 0.640–0.700，与人类标注者之间 0.616–0.689 的区间相当。
正文 · 原文
Abstract:The rapid expansion of scientific literature far outpaces the speed of manual curation, creating a fundamental bottleneck in extracting structured knowledge from scientific texts. To address this, we introduce an agentic, ontology-guided framework for knowledge graph (KG) construction. Our framework utilizes specialized agents for document understanding, information extraction, ontology conformance, and entity linking. First, an LLM extracts factual knowledge in the form of triples with explicit textual evidence from research papers. Then the triplets undergo a multistage verification process to ground the triplets in the ontology. By enforcing schema constraints and requiring evidence in the form of text fragments, we ensure the data is both semantically consistent and traceable. In an agreement study over 1,000 extracted triplets, Gemini-2.5-flash achieves Cohen's $\kappa$ scores of 0.640--0.700 against three human annotators, matching the human--human agreement range of 0.616--0.689. We applied this framework to 2,000 scientific publications and construct a novel, ontology-grounded KG for climate science with 133,990 nodes and 755,308 relations; of the 23,327 triplets that the publications contribute after validation, 98.96\% are judged correct. The pipeline code and KG is publicly available this https URL.
| Subjects: | Computation and Language (cs.CL); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.32725 [cs.CL] |
| (or arXiv:2610.32725v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.32725 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Aayush Acharya [view email]
[v1]
Fri, 23 Oct 2026 14:46:13 UTC (11,855 KB)
来源：arXiv cs.CL · arxiv.org