{"task":"Semantic entity labeling","dataset":"FUNSD","metric_names":["F1"],"rows":[{"id":131579,"task":"Semantic entity labeling","parent_task":null,"dataset":"FUNSD","model_name":"LayoutMask (large)","metrics":{"F1":"93.20"},"paper_url":"https://arxiv.org/abs/2305.18721v2","paper_title":"LayoutMask: Enhance Text-Layout Interaction in Multi-modal Pre-training for Document Understanding","paper_date":"2023-05-30","code_links":[],"metrics_order":"[\"F1\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":131580,"task":"Semantic entity labeling","parent_task":null,"dataset":"FUNSD","model_name":"ERNIE-Layoutlarge","metrics":{"F1":"93.12"},"paper_url":"https://arxiv.org/abs/2210.06155v2","paper_title":"ERNIE-Layout: Layout Knowledge Enhanced Pre-training for Visually-rich Document Understanding","paper_date":"2022-10-12","code_links":[{"title":"PaddlePaddle/PaddleNLP","url":"https://github.com/PaddlePaddle/PaddleNLP/tree/develop/model_zoo/ernie-layout"},{"title":"NormXU/ERNIE-Layout-Pytorch","url":"https://github.com/NormXU/ERNIE-Layout-Pytorch"}],"metrics_order":"[\"F1\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":131581,"task":"Semantic entity labeling","parent_task":null,"dataset":"FUNSD","model_name":"LayoutMask (base)","metrics":{"F1":"92.91"},"paper_url":"https://arxiv.org/abs/2305.18721v2","paper_title":"LayoutMask: Enhance Text-Layout Interaction in Multi-modal Pre-training for Document Understanding","paper_date":"2023-05-30","code_links":[],"metrics_order":"[\"F1\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":131582,"task":"Semantic entity labeling","parent_task":null,"dataset":"FUNSD","model_name":"GeoLayoutLM","metrics":{"F1":"92.86"},"paper_url":"https://arxiv.org/abs/2304.10759v1","paper_title":"GeoLayoutLM: Geometric Pre-training for Visual Information Extraction","paper_date":"2023-04-21","code_links":[{"title":"alibabaresearch/advancedliteratemachinery","url":"https://github.com/alibabaresearch/advancedliteratemachinery"}],"metrics_order":"[\"F1\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":131583,"task":"Semantic entity labeling","parent_task":null,"dataset":"FUNSD","model_name":"LayoutLMv3 Large","metrics":{"F1":"92.08"},"paper_url":"https://arxiv.org/abs/2204.08387v3","paper_title":"LayoutLMv3: Pre-training for Document AI with Unified Text and Image Masking","paper_date":"2022-04-18","code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"microsoft/unilm","url":"https://github.com/microsoft/unilm/tree/master/layoutlmv3"},{"title":"pwc-1/Paper-9","url":"https://github.com/pwc-1/Paper-9/tree/main/layoutlmv3"},{"title":"MindSpore-scientific-2/code-14","url":"https://github.com/MindSpore-scientific-2/code-14/tree/main/layoutlmv3"}],"metrics_order":"[\"F1\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":131584,"task":"Semantic entity labeling","parent_task":null,"dataset":"FUNSD","model_name":"RORE (GeoLayoutLM)","metrics":{"F1":"91.84"},"paper_url":"https://arxiv.org/abs/2409.19672v1","paper_title":"Modeling Layout Reading Order as Ordering Relations for Visually-rich Document Understanding","paper_date":"2024-09-29","code_links":[{"title":"chongzhangFDU/ROOR","url":"https://github.com/chongzhangFDU/ROOR"}],"metrics_order":"[\"F1\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":131585,"task":"Semantic entity labeling","parent_task":null,"dataset":"FUNSD","model_name":"StrucTexTv2 (large)","metrics":{"F1":"91.82"},"paper_url":"https://arxiv.org/abs/2303.00289v1","paper_title":"StrucTexTv2: Masked Visual-Textual Prediction for Document Image Pre-training","paper_date":"2023-03-01","code_links":[{"title":"PaddlePaddle/VIMER","url":"https://github.com/PaddlePaddle/VIMER/tree/main/StrucTexT/v2"}],"metrics_order":"[\"F1\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":131586,"task":"Semantic entity labeling","parent_task":null,"dataset":"FUNSD","model_name":"XDoc1M","metrics":{"F1":"89.4"},"paper_url":"https://arxiv.org/abs/2210.02849v1","paper_title":"XDoc: Unified Pre-training for Cross-Format Document Understanding","paper_date":"2022-10-06","code_links":[{"title":"microsoft/unilm","url":"https://github.com/microsoft/unilm/tree/master/xdoc"}],"metrics_order":"[\"F1\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":131587,"task":"Semantic entity labeling","parent_task":null,"dataset":"FUNSD","model_name":"StrucTexTv2 (small)","metrics":{"F1":"89.23"},"paper_url":"https://arxiv.org/abs/2303.00289v1","paper_title":"StrucTexTv2: Masked Visual-Textual Prediction for Document Image Pre-training","paper_date":"2023-03-01","code_links":[{"title":"PaddlePaddle/VIMER","url":"https://github.com/PaddlePaddle/VIMER/tree/main/StrucTexT/v2"}],"metrics_order":"[\"F1\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":131588,"task":"Semantic entity labeling","parent_task":null,"dataset":"FUNSD","model_name":"LILT","metrics":{"F1":"88.41"},"paper_url":"https://arxiv.org/abs/2202.13669v1","paper_title":"LiLT: A Simple yet Effective Language-Independent Layout Transformer for Structured Document Understanding","paper_date":"2022-02-28","code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"jpwang/lilt","url":"https://github.com/jpwang/lilt"},{"title":"pwc-1/Paper-9","url":"https://github.com/pwc-1/Paper-9/tree/main/lilt"},{"title":"MindSpore-scientific-2/code-14","url":"https://github.com/MindSpore-scientific-2/code-14/tree/main/lilt"},{"title":"MS-P3/code3","url":"https://github.com/MS-P3/code3/tree/main/lilt"}],"metrics_order":"[\"F1\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":131589,"task":"Semantic entity labeling","parent_task":null,"dataset":"FUNSD","model_name":"TPP (LayoutMask)","metrics":{"F1":"85.16"},"paper_url":"https://arxiv.org/abs/2310.11016v1","paper_title":"Reading Order Matters: Information Extraction from Visually-rich Documents by Token Path Prediction","paper_date":"2023-10-17","code_links":[{"title":"chongzhangfdu/tpp","url":"https://github.com/chongzhangfdu/tpp"},{"title":"WinterShiver/Token-Path-Prediction","url":"https://github.com/WinterShiver/Token-Path-Prediction"}],"metrics_order":"[\"F1\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":131590,"task":"Semantic entity labeling","parent_task":null,"dataset":"FUNSD","model_name":"LayoutLMv2LARGE","metrics":{"F1":"84.2"},"paper_url":"https://arxiv.org/abs/2012.14740v4","paper_title":"LayoutLMv2: Multi-modal Pre-training for Visually-Rich Document Understanding","paper_date":"2020-12-29","code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"PaddlePaddle/PaddleOCR","url":"https://github.com/PaddlePaddle/PaddleOCR"},{"title":"microsoft/unilm","url":"https://github.com/microsoft/unilm"},{"title":"PaddlePaddle/PaddleNLP","url":"https://github.com/PaddlePaddle/PaddleNLP/tree/develop/paddlenlp/transformers/layoutlmv2"},{"title":"facebookresearch/data2vec_vision","url":"https://github.com/facebookresearch/data2vec_vision"},{"title":"pwc-1/Paper-9","url":"https://github.com/pwc-1/Paper-9/tree/main/layoutlmv2"},{"title":"MS-P3/code3","url":"https://github.com/MS-P3/code3/tree/main/layoutlmv2"},{"title":"MindSpore-scientific-2/code-14","url":"https://github.com/MindSpore-scientific-2/code-14/tree/main/layoutlmv2"},{"title":"MindSpore-scientific/code-7","url":"https://github.com/MindSpore-scientific/code-7/tree/main/LayoutLMv2"}],"metrics_order":"[\"F1\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":131591,"task":"Semantic entity labeling","parent_task":null,"dataset":"FUNSD","model_name":"DocTr","metrics":{"F1":"84"},"paper_url":"https://arxiv.org/abs/2307.07929v1","paper_title":"DocTr: Document Transformer for Structured Information Extraction in Documents","paper_date":"2023-07-16","code_links":[],"metrics_order":"[\"F1\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":131592,"task":"Semantic entity labeling","parent_task":null,"dataset":"FUNSD","model_name":"LayoutLMv2BASE","metrics":{"F1":"82.76"},"paper_url":"https://arxiv.org/abs/2012.14740v4","paper_title":"LayoutLMv2: Multi-modal Pre-training for Visually-Rich Document Understanding","paper_date":"2020-12-29","code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"PaddlePaddle/PaddleOCR","url":"https://github.com/PaddlePaddle/PaddleOCR"},{"title":"microsoft/unilm","url":"https://github.com/microsoft/unilm"},{"title":"PaddlePaddle/PaddleNLP","url":"https://github.com/PaddlePaddle/PaddleNLP/tree/develop/paddlenlp/transformers/layoutlmv2"},{"title":"facebookresearch/data2vec_vision","url":"https://github.com/facebookresearch/data2vec_vision"},{"title":"pwc-1/Paper-9","url":"https://github.com/pwc-1/Paper-9/tree/main/layoutlmv2"},{"title":"MS-P3/code3","url":"https://github.com/MS-P3/code3/tree/main/layoutlmv2"},{"title":"MindSpore-scientific-2/code-14","url":"https://github.com/MindSpore-scientific-2/code-14/tree/main/layoutlmv2"},{"title":"MindSpore-scientific/code-7","url":"https://github.com/MindSpore-scientific/code-7/tree/main/LayoutLMv2"}],"metrics_order":"[\"F1\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":131593,"task":"Semantic entity labeling","parent_task":null,"dataset":"FUNSD","model_name":"Doc2Graph","metrics":{"F1":"82.25"},"paper_url":"https://arxiv.org/abs/2208.11168v1","paper_title":"Doc2Graph: a Task Agnostic Document Understanding Framework based on Graph Neural Networks","paper_date":"2022-08-23","code_links":[{"title":"andreagemelli/doc2graph","url":"https://github.com/andreagemelli/doc2graph"}],"metrics_order":"[\"F1\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]}]}