AgentMap: Joint Equivalence and Subsumption Discovery for Ontology Matching· AgentMap：联合等价和子集发现的本体匹配
Ontology matching (OM) has traditionally been formulated as either equivalence discovery or subsumption matching. The existing OM systems identify only one type of semantic correspondence and cannot simultaneously discover equivalence and subsumption mappings. In this paper, we introduce Hybrid Ontology Matching (HOM), a new OM task that unifies equivalence and subsumption discovery, and accordingly propose a Large Language Model (LLM)-based multi-agent OM framework AgentMap that is implemented by a series of interdependent semantic decisions. Given a concept in the source ontology, AgentMap integrates semantic retrieval, hierarchical search, and collaborative multi-agent LLM reasoning to progressively explore the target ontology, identifying either the equivalent concept, if one exists, o
本体匹配新框架AgentMap，同时发现等价和子集关系。
- 核心方法
- 提出Hybrid Ontology Matching (HOM)任务，利用AgentMap框架通过语义检索、层次搜索和多代理LLM推理逐步探索目标本体。
- 适合谁读
- 研究者 / 工程师
- 要解决的问题
- 现有的本体匹配系统只能识别一种类型的语义对应，无法同时发现等价和子集映射。
- 关键实验
- 未提供
- 主要贡献
- AgentMap能够同时处理等价和子集关系的发现，为复杂的本体匹配提供了一个新的解决方案。
- 意义与局限
- AgentMap的提出扩展了本体匹配的应用范围，提高了匹配的灵活性和准确性，但其实际效果需要通过实验验证。