User interaction is one of the most effective ways to improve the ontology alignment quality. However, this approach faces the challenge of how users can participate effectively in the matching process. To solve this challenge. In this paper, an interactive ontology alignment approach using compact differential evolution algorithm with adaptive parameter control (IOACDE) is proposed. In this method, the ontology alignment process is modeled as an interactive optimization problem and users are allowed to intervene in matching in two ways. One is that the mapping suggestions generated by IOACDE as a complete candidate alignment is evaluated by user during optimization process. The other is that the user ameliorates the alignment results by evaluating single mapping after the automatic matching process. To demonstrate the effectiveness of the proposed algorithm, the neural embedding model and K nearest neighbor (KNN) is employed to simulate user for the ontologies of the real world. The experimental results show that the proposed interactive approach can improve the alignment quality compared to the non-interactive. Compared with the state-of-the-art methods from OAEI, the results show that the proposed algorithm has a better performance under the same error rate.

翻译：用户交互是提升本体对齐质量最有效的方法之一。然而，该方法面临如何让用户有效参与匹配过程的挑战。为解决这一难题，本文提出了一种基于自适应参数控制紧凑差分进化算法的交互式本体对齐方法（IOACDE）。该方法将本体对齐过程建模为交互式优化问题，允许用户以两种方式干预匹配：其一是将IOACDE生成的映射建议作为完整候选对齐，在优化过程中由用户评估；其二是用户通过自动匹配过程后的单映射评估来改善对齐结果。为验证所提算法的有效性，采用神经嵌入模型和K近邻（KNN）模拟真实世界本体的用户行为。实验结果表明，与非交互式方法相比，所提出的交互式方法能有效提升对齐质量。与OAEI（本体对齐评估倡议）最新方法相比，在相同错误率下，本算法展现出更优性能。