Graph Neural Network Approach to Semantic Type Detection in Tables

TL;DR

This paper introduces a Graph Neural Network-based method for semantic type detection in tables, enhancing accuracy by modeling intra-table dependencies and leveraging language models more effectively.

Contribution

The study presents a novel GNN approach that improves semantic column type detection and provides insights into different GNN types' utility.

Findings

Outperforms existing algorithms in accuracy

Effectively models intra-table dependencies

Provides insights into GNN types for semantic detection

Abstract

This study addresses the challenge of detecting semantic column types in relational tables, a key task in many real-world applications. While language models like BERT have improved prediction accuracy, their token input constraints limit the simultaneous processing of intra-table and inter-table information. We propose a novel approach using Graph Neural Networks (GNNs) to model intra-table dependencies, allowing language models to focus on inter-table information. Our proposed method not only outperforms existing state-of-the-art algorithms but also offers novel insights into the utility and functionality of various GNN types for semantic type detection. The code is available at https://github.com/hoseinzadeehsan/GAIT