SemTabla: A Human-in-the-Loop Framework for Semantic Enrichment and Validation of Data Tables

要旨

Data tables are widely used to record critical information, enabling decision-makers to derive insights through table question answering (Table QA). However, the metadata from table schemas alone often fail to capture the underlying business semantics embedded in the tabular data, leading to reasoning errors. Existing automated approaches to semantic enrichment face challenges in insufficient data utilization, narrow feature coverage, and limited interpretability. To overcome these limitations, we propose SemTabla, an interactive system that employs a human-in-the-loop mechanism to extract comprehensive and interpretable semantics from tabular data. Our key contributions include: (1) a hierarchical framework for extracting semantic attributes; (2) a novel sampling method that identifies critical but rare row instances; and (3) an interactive interface that supports visualization, validation, and refinement of the extracted table semantics. A user study confirmed the system’s usability, and quantitative experiments demonstrate that the extracted semantics significantly enhance the reasoning capabilities of large language models.

受賞
Honorable Mention
著者
Zhuochen Jin
Huawei Cloud, Hangzhou, China
Yingjie Mi
Nanjing University, Nanjing, China
Yehang Zhu
Nanjing University, Nanjing, China
yichen yao
Nanjing University, Nanjing, China
Chongyang Yu
Nanjing University, Nanjing, China
Ke Xu
Nanjing University, Nanjing, China

会議: CHI 2026

ACM CHI Conference on Human Factors in Computing Systems

セッション: Steering and Evaluating Generative AI

P1 - Room 117
6 件の発表
2026-04-17 18:00:00
2026-04-17 19:30:00