{"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/information-extraction-from-visually-rich-1","title":"Information Extraction from Visually Rich Documents Using Directed Weighted Graph Neural Network","arxiv_id":null,"date":"2024-09-11","proceeding":"International Conference on Document Analysis and Recognition 2024 9","authors":["Hamza Gbada","Karim Kalti","Mohamed Ali Mahjoub"],"abstract":"This paper presents a novel approach to information extraction (IE) from visually rich documents (VRD) by employing a directed weighted graph representation to capture relationships among various VRD components. In contrast to conventional methods relying on spatial proximity through Euclidean distance, our approach aims to enhance performance by introducing a novel representation of relationships using directed weighted graphs. The information extraction task from VRD is treated as a node classification problem, leveraging graph convolutional networks that process the VRD graphs. We conducted evaluations on five real-world datasets, showcasing notable results and performances that align with established norms.","url_abs":"https://link.springer.com/chapter/10.1007/978-3-031-70552-6_15","url_pdf":"https://link.springer.com/chapter/10.1007/978-3-031-70552-6_15","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":"information-extraction-from-visually-rich-1","repo_url":"https://github.com/HamzaGbada/direct-neighbor-vrd","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"document-layout-analysis","task_name":"Document Layout Analysis"},{"task_slug":"graph-neural-network","task_name":"Graph Neural Network"},{"task_slug":"information-retrieval","task_name":"Information Retrieval"},{"task_slug":"key-information-extraction","task_name":"Key Information Extraction"},{"task_slug":"node-classification","task_name":"Node Classification"},{"task_slug":"document-understanding","task_name":"document understanding"}],"methods":[{"method_slug":"align","method_name":"ALIGN"},{"method_slug":"gcn","method_name":"GCN"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}