{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/chargrid-towards-understanding-2d-documents","title":"Chargrid: Towards Understanding 2D Documents","arxiv_id":"1809.08799","date":"2018-09-24","proceeding":"EMNLP 2018 10","authors":["Anoop Raveendra Katti","Christian Reisswig","Cordula Guder","Sebastian Brarda","Steffen Bickel","Johannes Höhne","Jean Baptiste Faddoul"],"abstract":"We introduce a novel type of text representation that preserves the 2D layout\nof a document. This is achieved by encoding each document page as a\ntwo-dimensional grid of characters. Based on this representation, we present a\ngeneric document understanding pipeline for structured documents. This pipeline\nmakes use of a fully convolutional encoder-decoder network that predicts a\nsegmentation mask and bounding boxes. We demonstrate its capabilities on an\ninformation extraction task from invoices and show that it significantly\noutperforms approaches based on sequential text or document images.","url_abs":"http://arxiv.org/abs/1809.08799v1","url_pdf":"http://arxiv.org/pdf/1809.08799v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"chargrid-towards-understanding-2d-documents","repo_url":"https://github.com/antoinedelplace/chargrid","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"chargrid-towards-understanding-2d-documents","repo_url":"https://github.com/sangeetNSK/ChargridTF-GPU","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"chargrid-towards-understanding-2d-documents","repo_url":"https://github.com/sciencefictionlab/chargrid-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"chargrid-towards-understanding-2d-documents","repo_url":"https://github.com/zinzinhust96/Chargrid-Tensorflow","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"chargrid-towards-understanding-2d-documents","repo_url":"https://github.com/thanhhau097/chargrid2d","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"document-understanding","task_name":"document understanding"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1809.08799","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}