TableParser: Automatic Table Parsing with Weak Supervision from Spreadsheets
![Thumbnail](/bitstream/handle/20.500.11850/530965/TableParser_SDU_AAAI22_CRC_large.pdf.jpg?sequence=5&isAllowed=y)
Open access
Date
2022-03-01Type
- Conference Paper
ETH Bibliography
yes
Altmetrics
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. Show more
Permanent link
https://doi.org/10.3929/ethz-b-000530965Publication status
publishedBook title
Proceedings of the Workshop on Scientific Document Understanding co-located with 36th AAAI Conference on Artificial Inteligence (AAAI 2022)Journal / series
CEUR Workshop ProceedingsVolume
Pages / Article No.
Publisher
RWTH AachenEvent
Subject
Computer vision; pattern extraction; Document analyticsOrganisational unit
02120 - Dep. Management, Technologie und Ökon. / Dep. of Management, Technology, and Ec.09588 - Zhang, Ce (ehemalig) / Zhang, Ce (former)
03840 - Egger, Peter / Egger, Peter
Funding
204647 - How China Climbs the Tree of Trade Success (SNF)
Related publications and datasets
Is part of: https://ceur-ws.org/Vol-3164/
Notes
Conference lecture held on March 1, 2022More
Show all metadata
ETH Bibliography
yes
Altmetrics