{"url":"/sota/semantic-entity-labeling-on-funsd","task":{"name":"Semantic entity labeling","url":"/task/semantic-entity-labeling","note":null},"dataset":{"name":"FUNSD","url":"/dataset/funsd"},"category":"Natural Language Processing","categories":["Natural Language Processing"],"category_note":null,"description":"- One of Form Understanding task (Word grouping, Semantic entity labeling, Entity linking)\r\n- Classifying entities into one of four pre-defined categories: question, answer, header and, other.\r\n\r\ncited from\r\n\r\nG. Jaume, H. K. Ekenel, J. Thiran \"FUNSD: A Dataset for Form Understanding in Noisy Scanned Documents,\" 2019","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["F1"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"F1":"higher"}},"counts":{"rows":15,"rows_with_code":12,"rows_with_paper_page":15,"rows_dated":15,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"LayoutMask (large)","metrics":{"F1":"93.20"},"uses_additional_data":false,"paper_date":"2023-05-30","paper":"/paper/layoutmask-enhance-text-layout-interaction-in","paper_url":"https://arxiv.org/abs/2305.18721v2","paper_title":"LayoutMask: Enhance Text-Layout Interaction in Multi-modal Pre-training for Document Understanding","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":2,"model":"ERNIE-Layoutlarge","metrics":{"F1":"93.12"},"uses_additional_data":false,"paper_date":"2022-10-12","paper":"/paper/ernie-layout-layout-knowledge-enhanced-pre","paper_url":"https://arxiv.org/abs/2210.06155v2","paper_title":"ERNIE-Layout: Layout Knowledge Enhanced Pre-training for Visually-rich Document Understanding","code":"https://github.com/PaddlePaddle/PaddleNLP/tree/develop/model_zoo/ernie-layout","n_code_links":2,"syntology":{"n_ran":2,"n_unverified":5,"n_samples":7,"n_pointer_only_licence":0}},{"rank_in_archive_order":3,"model":"LayoutMask (base)","metrics":{"F1":"92.91"},"uses_additional_data":false,"paper_date":"2023-05-30","paper":"/paper/layoutmask-enhance-text-layout-interaction-in","paper_url":"https://arxiv.org/abs/2305.18721v2","paper_title":"LayoutMask: Enhance Text-Layout Interaction in Multi-modal Pre-training for Document Understanding","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":4,"model":"GeoLayoutLM","metrics":{"F1":"92.86"},"uses_additional_data":false,"paper_date":"2023-04-21","paper":"/paper/geolayoutlm-geometric-pre-training-for-visual","paper_url":"https://arxiv.org/abs/2304.10759v1","paper_title":"GeoLayoutLM: Geometric Pre-training for Visual Information Extraction","code":"https://github.com/alibabaresearch/advancedliteratemachinery","n_code_links":1,"syntology":null},{"rank_in_archive_order":5,"model":"LayoutLMv3 Large","metrics":{"F1":"92.08"},"uses_additional_data":false,"paper_date":"2022-04-18","paper":"/paper/layoutlmv3-pre-training-for-document-ai-with","paper_url":"https://arxiv.org/abs/2204.08387v3","paper_title":"LayoutLMv3: Pre-training for Document AI with Unified Text and Image Masking","code":"https://github.com/huggingface/transformers","n_code_links":4,"syntology":null},{"rank_in_archive_order":6,"model":"RORE (GeoLayoutLM)","metrics":{"F1":"91.84"},"uses_additional_data":false,"paper_date":"2024-09-29","paper":"/paper/modeling-layout-reading-order-as-ordering","paper_url":"https://arxiv.org/abs/2409.19672v1","paper_title":"Modeling Layout Reading Order as Ordering Relations for Visually-rich Document Understanding","code":"https://github.com/chongzhangFDU/ROOR","n_code_links":1,"syntology":null},{"rank_in_archive_order":7,"model":"StrucTexTv2 (large)","metrics":{"F1":"91.82"},"uses_additional_data":false,"paper_date":"2023-03-01","paper":"/paper/structextv2-masked-visual-textual-prediction","paper_url":"https://arxiv.org/abs/2303.00289v1","paper_title":"StrucTexTv2: Masked Visual-Textual Prediction for Document Image Pre-training","code":"https://github.com/PaddlePaddle/VIMER/tree/main/StrucTexT/v2","n_code_links":1,"syntology":null},{"rank_in_archive_order":8,"model":"XDoc1M","metrics":{"F1":"89.4"},"uses_additional_data":false,"paper_date":"2022-10-06","paper":"/paper/xdoc-unified-pre-training-for-cross-format","paper_url":"https://arxiv.org/abs/2210.02849v1","paper_title":"XDoc: Unified Pre-training for Cross-Format Document Understanding","code":"https://github.com/microsoft/unilm/tree/master/xdoc","n_code_links":1,"syntology":null},{"rank_in_archive_order":9,"model":"StrucTexTv2 (small)","metrics":{"F1":"89.23"},"uses_additional_data":false,"paper_date":"2023-03-01","paper":"/paper/structextv2-masked-visual-textual-prediction","paper_url":"https://arxiv.org/abs/2303.00289v1","paper_title":"StrucTexTv2: Masked Visual-Textual Prediction for Document Image Pre-training","code":"https://github.com/PaddlePaddle/VIMER/tree/main/StrucTexT/v2","n_code_links":1,"syntology":null},{"rank_in_archive_order":10,"model":"LILT","metrics":{"F1":"88.41"},"uses_additional_data":false,"paper_date":"2022-02-28","paper":"/paper/lilt-a-simple-yet-effective-language","paper_url":"https://arxiv.org/abs/2202.13669v1","paper_title":"LiLT: A Simple yet Effective Language-Independent Layout Transformer for Structured Document Understanding","code":"https://github.com/huggingface/transformers","n_code_links":5,"syntology":{"n_ran":2,"n_unverified":1,"n_samples":3,"n_pointer_only_licence":0}},{"rank_in_archive_order":11,"model":"TPP (LayoutMask)","metrics":{"F1":"85.16"},"uses_additional_data":false,"paper_date":"2023-10-17","paper":"/paper/reading-order-matters-information-extraction","paper_url":"https://arxiv.org/abs/2310.11016v1","paper_title":"Reading Order Matters: Information Extraction from Visually-rich Documents by Token Path Prediction","code":"https://github.com/chongzhangfdu/tpp","n_code_links":2,"syntology":null},{"rank_in_archive_order":12,"model":"LayoutLMv2LARGE","metrics":{"F1":"84.2"},"uses_additional_data":false,"paper_date":"2020-12-29","paper":"/paper/layoutlmv2-multi-modal-pre-training-for","paper_url":"https://arxiv.org/abs/2012.14740v4","paper_title":"LayoutLMv2: Multi-modal Pre-training for Visually-Rich Document Understanding","code":"https://github.com/huggingface/transformers","n_code_links":9,"syntology":null},{"rank_in_archive_order":13,"model":"DocTr","metrics":{"F1":"84"},"uses_additional_data":false,"paper_date":"2023-07-16","paper":"/paper/doctr-document-transformer-for-structured","paper_url":"https://arxiv.org/abs/2307.07929v1","paper_title":"DocTr: Document Transformer for Structured Information Extraction in Documents","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":14,"model":"LayoutLMv2BASE","metrics":{"F1":"82.76"},"uses_additional_data":false,"paper_date":"2020-12-29","paper":"/paper/layoutlmv2-multi-modal-pre-training-for","paper_url":"https://arxiv.org/abs/2012.14740v4","paper_title":"LayoutLMv2: Multi-modal Pre-training for Visually-Rich Document Understanding","code":"https://github.com/huggingface/transformers","n_code_links":9,"syntology":null},{"rank_in_archive_order":15,"model":"Doc2Graph","metrics":{"F1":"82.25"},"uses_additional_data":false,"paper_date":"2022-08-23","paper":"/paper/doc2graph-a-task-agnostic-document","paper_url":"https://arxiv.org/abs/2208.11168v1","paper_title":"Doc2Graph: a Task Agnostic Document Understanding Framework based on Graph Neural Networks","code":"https://github.com/andreagemelli/doc2graph","n_code_links":1,"syntology":null}],"since_archive":{"present":false,"note":"No Syntology-extracted rows are published in this build."},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":2,"rows_with_any_sample_ran":2,"distinct_papers_with_graph_line":2,"distinct_papers_with_any_sample_ran":2,"samples_over_distinct_papers":{"n_ran":4,"n_unverified":6,"n_samples":10,"n_pointer_only_licence":0,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":4,"n_unverified":6,"n_samples":10,"n_pointer_only_licence":0,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}