Discovery-Driven Integration of Disjoint Tables via Text
LOKI learns row-sentence links to join disjoint data-lake tables, with 0.982 precision and far lower LLM cost.
Researchers formalize Text-Mediated Join Path Discovery for integrating semantically related data-lake tables that lack explicit join attributes. LOKI uses horizontal bidirectional cross-attention and a global table-text contrastive objective so fine-grained row-sentence associations emerge without local supervision. It converts those links into interpretable join paths and typed integrated tables with sentence-level provenance. On real benchmarks it outperforms multi-modal discovery methods, with 0.982 macro typed-pair precision and up to 40 times lower LLM API cost than direct prompting.
- Formalizes Text-Mediated Join Path Discovery for tables lacking join keys.
- Contrastive training finds row-sentence links without local supervision.
- Reports 0.982 macro typed-pair precision and up to 40× lower LLM cost.
From the original article
1 min read at arxiv.orgIntegrating 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.
By Md Ataur Rahman · arxiv.org
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.