{"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/hypergraph-based-understanding-for-document","title":"Hypergraph based Understanding for Document Semantic Entity Recognition","arxiv_id":"2407.06904","date":"2024-07-09","proceeding":null,"authors":["Qiwei Li","Zuchao Li","Ping Wang","Haojun Ai","Hai Zhao"],"abstract":"Semantic entity recognition is an important task in the field of visually-rich document understanding. It distinguishes the semantic types of text by analyzing the position relationship between text nodes and the relation between text content. The existing document understanding models mainly focus on entity categories while ignoring the extraction of entity boundaries. We build a novel hypergraph attention document semantic entity recognition framework, HGA, which uses hypergraph attention to focus on entity boundaries and entity categories at the same time. It can conduct a more detailed analysis of the document text representation analyzed by the upstream model and achieves a better performance of semantic information. We apply this method on the basis of GraphLayoutLM to construct a new semantic entity recognition model HGALayoutLM. Our experiment results on FUNSD, CORD, XFUND and SROIE show that our method can effectively improve the performance of semantic entity recognition tasks based on the original model. The results of HGALayoutLM on FUNSD and XFUND reach the new state-of-the-art results.","url_abs":"https://arxiv.org/abs/2407.06904v1","url_pdf":"https://arxiv.org/pdf/2407.06904v1.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":"hypergraph-based-understanding-for-document","repo_url":"https://github.com/Line-Kite/HGALayoutLM","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"document-understanding","task_name":"document understanding"}],"methods":[{"method_slug":"attention","method_name":"Attention"},{"method_slug":"focus","method_name":"Focus"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2407.06904","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.06904"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"deterministic:regex_extraction","url":"https://github.com/Lyken17/pytorch-OpCounter","reach":null},{"provenance":"deterministic:regex_extraction","url":"https://github.com/Line-Kite/HGALayoutLM","reach":{"status":"ok"}}],"summary":{"ran":6},"by_repo_kind":{"official":{"samples":6,"ran":6,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":6,"samples":[{"code_sha256_prefix":"8dacfd39c4a41e17","entry":"crop","repo":"Line-Kite/HGALayoutLM","repo_kind":"official","path":"utils/image_utils.py","file_url":"https://github.com/Line-Kite/HGALayoutLM/blob/HEAD/utils/image_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"8dacfd39c4a41e17"}},{"code_sha256_prefix":"8ea97f6b5e77a0f4","entry":"json_loader","repo":"Line-Kite/HGALayoutLM","repo_kind":"official","path":"utils/graph_builder_uitls.py","file_url":"https://github.com/Line-Kite/HGALayoutLM/blob/HEAD/utils/graph_builder_uitls.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"8ea97f6b5e77a0f4"}},{"code_sha256_prefix":"c23469a99394f25f","entry":"normalize_bbox","repo":"Line-Kite/HGALayoutLM","repo_kind":"official","path":"utils/image_utils.py","file_url":"https://github.com/Line-Kite/HGALayoutLM/blob/HEAD/utils/image_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c23469a99394f25f"}},{"code_sha256_prefix":"739884d68f7e0bd2","entry":"posotion_judge","repo":"Line-Kite/HGALayoutLM","repo_kind":"official","path":"utils/graph_builder_uitls.py","file_url":"https://github.com/Line-Kite/HGALayoutLM/blob/HEAD/utils/graph_builder_uitls.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"739884d68f7e0bd2"}},{"code_sha256_prefix":"87320a38b510a8c8","entry":"set_edges","repo":"Line-Kite/HGALayoutLM","repo_kind":"official","path":"utils/graph_utils.py","file_url":"https://github.com/Line-Kite/HGALayoutLM/blob/HEAD/utils/graph_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"87320a38b510a8c8"}},{"code_sha256_prefix":"4fdc6cc217a701d5","entry":"set_nodes","repo":"Line-Kite/HGALayoutLM","repo_kind":"official","path":"utils/graph_utils.py","file_url":"https://github.com/Line-Kite/HGALayoutLM/blob/HEAD/utils/graph_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"4fdc6cc217a701d5"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}