Generative Ontology Induction: Domain-Agnostic Schema Discovery from Document Corpora Using Large Language Models
Generative Ontology Induction: Domain-Agnostic Schema Discovery from Document Corpora Using Large Language Models
生成式本体归纳：利用大语言模型从文档语料库中进行领域无关的模式发现
Abstract: Ontology engineering remains a critical bottleneck in knowledge-intensive AI systems. Existing automated approaches either depend on predefined schemas, operate within narrow domains, or produce unstructured outputs unsuitable for downstream pipelines.
摘要： 本体工程仍然是知识密集型人工智能系统中的关键瓶颈。现有的自动化方法要么依赖于预定义的模式，要么局限于狭窄的领域，要么产生不适合下游流程的非结构化输出。
We introduce Generative Ontology Induction (GOI), a domain-agnostic framework that induces a generative blueprint - entities, dimensions, properties, relationships, and constraints - from a corpus of examples and exports it as a typed graph (six node types, seven edge types) in YAML/JSON.
我们引入了生成式本体归纳（Generative Ontology Induction, GOI），这是一个领域无关的框架。它能从示例语料库中归纳出生成蓝图（包括实体、维度、属性、关系和约束），并将其导出为 YAML/JSON 格式的类型化图谱（包含六种节点类型和七种边类型）。
We introduce the Node Coverage Score, a novel evaluation metric that measures the fraction of structural ontology nodes (classes, properties, and dimensions) appearing in generated outputs.
我们引入了“节点覆盖分数”（Node Coverage Score），这是一种衡量生成输出中结构化本体节点（类、属性和维度）占比的新型评估指标。
A controlled generative validation on four contrasting ontologies - a familiar Software Services Invoice schema, a custom Job Description Ontology, a confidential Pain-Management Clinical Visit Record Ontology, and a Professional Services Contract & Statement of Work Ontology - shows that GOI-prompted generation covers 95-100% of the structural backbone in every case; a generic three-field template holds at 97.8% on the invoice schema but drops to 52.2% on the Job Description Ontology, 62.2% on the Pain-Management ontology, and 78.3% on the Professional Services Contract ontology.
通过对四种对比鲜明的本体进行受控生成验证——包括常见的软件服务发票模式、自定义职位描述本体、机密的疼痛管理临床就诊记录本体，以及专业服务合同与工作说明书本体——结果显示，GOI 提示生成的方案在每种情况下都能覆盖 95-100% 的结构骨架；相比之下，通用的三字段模板在发票模式上表现为 97.8%，但在职位描述本体上降至 52.2%，在疼痛管理本体上降至 62.2%，在专业服务合同本体上降至 78.3%。
The structural coverage holds regardless of how familiar the document type is to the model.
无论模型对文档类型的熟悉程度如何，这种结构覆盖率都能保持稳定。