大语言模型辅助的本体工程与法国法律知识图谱构建
LLM-Assisted Ontology Engineering and Construction of a French Legal Knowledge Graph
浏览论文内容
中文总结 AI 辅助
针对法国维护法规处理难题，提出两阶段大语言模型辅助工作流程，先进行本体工程，再构建知识图谱。经实验，该流程输出强大、对齐良好，减少重复，明确关键细化步骤。
中文摘要 AI 辅助
维护法规是复杂的法律文本，处理特定案例时难以利用，且难以集成到操作系统中。本文提出了一个两阶段的大语言模型辅助工作流程，用于处理法国维护法规：从基于SEMLEG的核心本体进行本体工程，然后构建基于本体的法国法律知识图谱。第一阶段包括从分层语料库样本中开放提取类型化实体和三元组，通过基于嵌入的融合对标签进行归一化，以及诱导候选对象属性及其签名（域和范围）。第二阶段使用生成的本体指导在整个语料库上进行三元组的封闭提取和RDF图构建。使用GPT-4.1和米斯特拉尔-large-2512进行的实验显示出强大的结构化输出、近乎完整的类对齐，以及融合后重复实体和谓词的大幅减少。不到20%的三元组引入了未见属性，而较低的精确签名合规性揭示了现有谓词的新域-范围组合。这些结果表明谓词归一化和新观察到的关系签名的验证是工业维护设置中的关键细化步骤。
英文摘要
Maintenance regulations are complex legal texts that are difficult to exploit when addressing a specific case and challenging to integrate into operational systems. This paper presents a two-stage LLM-assisted workflow for French maintenance regulations: ontology engineering from a SEMLEG-based core ontology, followed by construction of an ontology-grounded French legal knowledge graph. The first stage consists in the open extraction of typed entities and triples from a stratified corpus sample, the normalization of labels through embedding-based fusion, and the induction of candidate object properties with their signature (domain and range). The second stage uses the resulting ontology to guide the closed extraction of triples and RDF graph construction over the full corpus. Experiments with GPT-4.1 and mistral-large-2512 show robust structured outputs, near-complete class alignment, and a substantial reduction of duplicated entities and predicates after fusion. Fewer than 20% of triples introduce unseen properties, while lower exact signature compliance reveals new domain-range combinations for existing predicates. These results point to predicate normalization and the validation of newly observed relation signatures as key refinement steps for industrial maintenance settings.
发表机构
- Université Côte d'Azur（蔚蓝海岸大学）
- Inria（法国国家信息与自动化研究所）
- CNRS（法国国家科学研究中心）
- Berger-Levrault（贝尔热-勒弗罗公司）
机构由 AI 辅助整理，请以论文原文为准。
