arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2602.04004cs.DB
收藏

StraTyper:自动化语义类型发现与多类型注解用于数据集集合

StraTyper: Automated Semantic Type Discovery and Multi-Type Annotation for Dataset Collections

New York University(纽约大学)

Christos Koutras, Juliana Freire

AI总结:

StraTyper通过自动化语义类型发现和多类型注解,有效解决数据集语义理解中的类型冗余和覆盖不足问题,提升下游任务性能。

摘要:

理解数据集的语义对于有效的搜索、发现和集成流程至关重要。为此,列类型注解(CTA)方法通过预训练的深度学习模型或大型语言模型(LLMs)将表格数据集的列与能准确描述其内容的语义类型关联起来。然而,现有方法要求用户在训练或推理时指定一个封闭的语义类型集合,这阻碍了其在领域特定数据集上的应用,因为预定义标签往往缺乏足够的覆盖性和特异性。此外,现实世界的数据集经常包含属于多种语义类型的列值,违反了现有CTA方法的单类型假设。尽管专有LLMs在CTA方面表现出色,但它们会产生高昂的货币成本,并且对于相似的列会产生不一致的输出,导致类型冗余,从而影响下游应用。为了解决这些挑战,我们介绍了StraTyper,一种成本效益高的方法,用于数据集集合中的列类型发现(CTD)和多类型注解(CMTA)。StraTyper通过系统地利用LLMs来发现适合数据集集合的类型,消除了对预定义语义标签的需求。通过战略性的列聚类、受控的类型生成和迭代级联发现,StraTyper在平衡类型精度与注解覆盖范围的同时,最小化LLM成本。我们的实验评估——包括人工和LLM辅助的现实世界基准测试——表明,StraTyper能够准确发现数值和非数值数据的类型,相比商业LLMs实现显著的成本节省,并有效处理多类型列。我们进一步表明,StraTyper的注解提高了下游任务,包括连接发现和模式匹配,优于仅使用LLM的基线。

英文摘要:

Understanding dataset semantics is crucial for effective search, discovery, and integration pipelines. To this end, column-type annotation (CTA) methods associate columns in tabular datasets with semantic types that accurately describe their contents, using pretrained deep learning models or Large Language Models (LLMs). However, existing approaches have important limitations. First, they require users to specify a closed set of semantic types either during training or inference, which hinders their application to domain-specific datasets where predefined type vocabularies often lack adequate coverage and specificity. They also assume that each column is associated with a single semantic type, an assumption that does not hold for many real-world datasets. Lastly, while proprietary LLMs have shown effectiveness for CTA, they incur high monetary costs and produce inconsistent outputs across similar columns, leading to type redundancy that degrades downstream applications. To address these challenges, we introduce StraTyper, a cost-effective method for column type discovery (CTD) and multi-type annotation (CMTA) in dataset collections. StraTyper eliminates the need for predefined semantic labels by employing LLMs to discover types tailored to the target dataset collection. Through strategic column clustering, controlled type generation, and iterative cascading discovery, StraTyper balances type precision with annotation coverage while minimizing LLM costs. Our experimental evaluation, both manual and LLM-assisted, on real-world dataset collections demonstrates that StraTyper discovers accurate types for both numeric and textual data, achieves substantial cost savings over commercial LLMs, and effectively handles multi-typed columns. We further show that StraTyper's annotations improve downstream tasks, including join discovery and schema matching, outperforming LLM-only baselines.

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。

↑