ACL2025
RelationalCoder: Rethinking Complex Tables via Programmatic Relational Transformation
Haoyu Dong, Yue Hu, Huailiang Peng, Yanan Cao
Abstract
Semi-structured tables, with their varied layouts and formatting artifacts, remain a major obstacle for automated data processing and analytics. To address these challenges, we propose RELATIONALCODER, which uniformly converts semi-structured tables into relational data, enabling smooth integration with the rich ecosystem of data processing and analytics tools. By leveraging SQL code, RELATIONAL-CODER prevents schema errors and markedly improves normalization quality across multiple relational tables.