Handling big tabular data of ICT supply chains: a multi-task, machine-interpretable approach

TL;DR

This paper introduces a multi-task approach for interpreting complex ICT supply chain tables, transforming them into machine-readable formats by recognizing structure and classifying cell types, improving accuracy over existing methods.

Contribution

The paper proposes a novel multi-task model that simultaneously performs table structure recognition and cell type classification using multimodal features, advancing automated ICT supply chain data interpretation.

Findings

Outperforms state-of-the-art on ICDAR2013 dataset

Effective multi-task learning with multimodal features

Improves accuracy in table structure and cell classification

Abstract

Due to the characteristics of Information and Communications Technology (ICT) products, the critical information of ICT devices is often summarized in big tabular data shared across supply chains. Therefore, it is critical to automatically interpret tabular structures with the surging amount of electronic assets. To transform the tabular data in electronic documents into a machine-interpretable format and provide layout and semantic information for information extraction and interpretation, we define a Table Structure Recognition (TSR) task and a Table Cell Type Classification (CTC) task. We use a graph to represent complex table structures for the TSR task. Meanwhile, table cells are categorized into three groups based on their functional roles for the CTC task, namely Header, Attribute, and Data. Subsequently, we propose a multi-task model to solve the defined two tasks simultaneously by using the text modal and image modal features. Our experimental results show that our proposed method can outperform state-of-the-art methods on ICDAR2013 and UNLV datasets.