arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2403.01567cs.DBcs.AI
收藏

ReMatch:基于LLM的检索增强模式匹配

ReMatch: Retrieval Enhanced Schema Matching with LLMs

Microsoft(微软公司)

Eitam Sheetrit, Menachem Brief, Moshik Mishaeli, Oren Elisha

AI总结:

本文提出ReMatch,一种基于检索增强LLM的模式匹配方法,无需预定义映射、模型训练或源数据访问,在大型真实模式上表现有效,适用于现实场景。

摘要:

模式匹配是数据集成中的一项关键任务,涉及将源模式与目标模式对齐,以建立其元素之间的对应关系。由于文本和语义的异构性以及模式大小的差异,该任务具有挑战性。尽管基于机器学习的解决方案已在众多研究中被探索,但它们通常准确率低,需要为模型训练手动映射模式,或需要访问源模式数据(这可能会因隐私问题而无法获取)。在本文中,我们提出了一种名为ReMatch的新方法,该方法使用检索增强的大型语言模型(LLM)来匹配模式。我们的方法避免了预定义映射、任何模型训练或访问源数据库中的数据。我们在大型真实模式上的实验结果表明,ReMatch是一个有效的匹配器。通过消除对训练数据的需求,ReMatch成为现实场景中的可行解决方案。

英文摘要:

Schema matching is a crucial task in data integration, involving the alignment of a source schema with a target schema to establish correspondence between their elements. This task is challenging due to textual and semantic heterogeneity, as well as differences in schema sizes. Although machine-learning-based solutions have been explored in numerous studies, they often suffer from low accuracy, require manual mapping of the schemas for model training, or need access to source schema data which might be unavailable due to privacy concerns. In this paper we present a novel method, named ReMatch, for matching schemas using retrieval-enhanced Large Language Models (LLMs). Our method avoids the need for predefined mapping, any model training, or access to data in the source database. Our experimental results on large real-world schemas demonstrate that ReMatch is an effective matcher. By eliminating the requirement for training data, ReMatch becomes a viable solution for real-world scenarios.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑