发表机构
UPC, BarcelonaTech; Université Libre de Bruxelles（加泰罗尼亚理工大学，巴塞罗那理工; 布鲁塞尔自由大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对数据湖中缺乏显式连接属性的不相交表，提出LOKI架构，通过文本介导发现细粒度行-句关联并物化为可解释的类型化集成表，在真实基准上精度达0.982且成本降低40倍。
AI 中文摘要
在数据湖中集成异构数据集是一个关键挑战，尤其是对于缺乏显式连接属性的语义相关表。我们研究发现驱动型集成，在此设置中，相关源及其缺失的关系结构必须在集成之前被发现。在此设置中，非结构化文本提供了连接原本不相交表的证据。根本挑战在于在细粒度级别发现关系，通过特定句子连接不同表中的单个行。我们将此任务形式化为文本介导的连接路径发现，并提出一种称为LOKI（潜在空间优化用于知识集成）的水平双向交叉注意力架构，该架构学习表行和句子的上下文表示。通过全局表-文本对比目标，细粒度的行-句子关联在无需显式局部监督的情况下出现。现有的多模态发现方法主要检索粗粒度的列-文本关联，而集成系统假设提供了行-文本链接、模式或查询。LOKI反而将这些隐式关联转化为显式、可解释的连接路径，将其组织成关系一致的组，并将其物化为具有句子级来源的类型化集成表。在真实世界基准上的全面评估表明，LOKI持续优于最先进的多模态数据发现方法，并以0.982的宏类型对精度物化类型化集成表，同时其LLM API成本比直接提示便宜多达40倍。
英文摘要
Integrating heterogeneous datasets within data lakes is a critical challenge, particularly for semantically related tables that lack the explicit attributes needed to be joined. We study Discovery-Driven Integration, where the relevant sources and their missing relational structure must be discovered before integration. In this setting, unstructured text provides the evidence that connects otherwise disjoint tables. The fundamental challenge is to discover the relationships at a fine-grained level that connect individual rows from different tables through specific sentences. We formalize this task as Text-Mediated Join Path Discovery and propose a horizontal bidirectional cross-attention architecture called LOKI Latent-space Optimization for Knowledge Integration) that learns contextualized representations of table rows and sentences. Through a global table-text contrastive objective, fine-grained row-sentence associations emerge without explicit local supervision. Existing multi-modal discovery methods largely retrieve coarse-grained column-text associations, whereas integration systems assume supplied row-text links, schemas, or queries. LOKI instead transforms these implicit associations into explicit, interpretable join paths, organizes them into relation-consistent groups, and materializes them as typed integrated tables with sentence-level provenance. Comprehensive evaluations on real-world benchmarks demonstrate that LOKI consistently outperforms state-of-the-art multi-modal data discovery approaches, and materializes typed integrated tables with 0.982 macro typed-pair precision while being up to 40 times cheaper in LLM API cost than direct prompting.
