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

2026-02-03

AI Summary

Existing column type annotation methods are constrained by predefined semantic type vocabularies, limiting their applicability to domain-specific data and their ability to handle columns with multiple semantic types. Meanwhile, commercial large language models suffer from high costs and unstable outputs. To address these limitations, this work proposes StraTyper, a method that automatically discovers dataset-adaptive semantic types without relying on predefined labels and supports multi-type annotations. Its core innovation lies in integrating column clustering, controlled type generation, and a cascaded iterative discovery mechanism, which collectively achieve high-precision, high-coverage semantic typing while substantially reducing the cost of large model invocations. Experiments demonstrate that StraTyper effectively identifies semantic types for both numeric and non-numeric columns on real-world datasets, significantly lowering annotation costs and enhancing downstream tasks such as join discovery and schema matching.

Technology Category

• Constraint Satisfaction and Optimization: Satisfiability Modulo Theories
• Machine Learning: Statistical Relational/Logic Learning
• Natural Language Processing: Sentence-level Semantics, Textual Inference, etc.

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Humans versus LLMs for data annotation and labeling
• Search and Retrieval-Augmented AI: Vertical and domain-specific search

Abstract

Understanding dataset semantics is crucial for effective search, discovery, and integration pipelines. To this end, column type annotation (CTA) methods associate columns of tabular datasets with semantic types that accurately describe their contents, using pre-trained deep learning models or Large Language Models (LLMs). However, existing approaches require users to specify a closed set of semantic types either at training or inference time, hindering their application to domain-specific datasets where pre-defined labels often lack adequate coverage and specificity. Furthermore, real-world datasets frequently contain columns with values belonging to multiple semantic types, violating the single-type assumption of existing CTA methods. While proprietary LLMs have shown effectiveness for CTA, they incur high monetary costs and produce inconsistent outputs for similar columns, leading to type redundancy that negatively affects 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 pre-defined semantic labels by systematically employing LLMs to discovery types tailored to the dataset collection at hand. 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 benchmarks demonstrates that StraTyper discovers accurate types for both numerical and non-numerical data, achieves substantial cost savings compared to 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.

Problem

• column type annotation
• semantic type discovery
• multi-type columns
• dataset semantics
• LLM inconsistency

Innovation

• Semantic Type Discovery
• Multi-Type Annotation
• Column Type Annotation
• Large Language Models
• Cost-Efficient LLM Usage