TableParser: Automatic Table Parsing with Weak Supervision from Spreadsheets

TL;DR

TableParser is a system that accurately extracts table structures and content from PDFs and images using weak supervision from spreadsheets, advancing automated data extraction techniques.

Contribution

The paper introduces TableParser, a novel system capable of parsing tables in PDFs and images with high accuracy, utilizing a new weak supervision approach with supporting annotation tools.

Findings

High precision in table parsing demonstrated

Effective domain adaptation techniques employed

Resources shared to promote further research

Abstract

Tables have been an ever-existing structure to store data. There exist now different approaches to store tabular data physically. PDFs, images, spreadsheets, and CSVs are leading examples. Being able to parse table structures and extract content bounded by these structures is of high importance in many applications. In this paper, we devise TableParser, a system capable of parsing tables in both native PDFs and scanned images with high precision. We have conducted extensive experiments to show the efficacy of domain adaptation in developing such a tool. Moreover, we create TableAnnotator and ExcelAnnotator, which constitute a spreadsheet-based weak supervision mechanism and a pipeline to enable table parsing. We share these resources with the research community to facilitate further research in this interesting direction.