{"task":"Relation Extraction","dataset":"FUNSD","metric_names":["F1"],"rows":[{"id":8365,"task":"Relation Extraction","parent_task":null,"dataset":"FUNSD","model_name":"LayoutLMv3 large EM + BBO + RSF","metrics":{"F1":"90.81"},"paper_url":"https://arxiv.org/abs/2404.10848v1","paper_title":"A LayoutLMv3-Based Model for Enhanced Relation Extraction in Visually-Rich Documents","paper_date":"2024-04-16","code_links":[],"metrics_order":"[\"F1\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":8366,"task":"Relation Extraction","parent_task":null,"dataset":"FUNSD","model_name":"GeoLayoutLM","metrics":{"F1":"89.45"},"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":8367,"task":"Relation Extraction","parent_task":null,"dataset":"FUNSD","model_name":"RORE (GeoLayoutLM)","metrics":{"F1":"88.46"},"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":8368,"task":"Relation Extraction","parent_task":null,"dataset":"FUNSD","model_name":"LayoutLMv3 large","metrics":{"F1":"80.35"},"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":8369,"task":"Relation Extraction","parent_task":null,"dataset":"FUNSD","model_name":"LayoutLMv3 large","metrics":{"F1":"80.35"},"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":8370,"task":"Relation Extraction","parent_task":null,"dataset":"FUNSD","model_name":"TPP (LayoutMask)","metrics":{"F1":"79.20"},"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":8371,"task":"Relation Extraction","parent_task":null,"dataset":"FUNSD","model_name":"BROS","metrics":{"F1":"77.01"},"paper_url":"https://arxiv.org/abs/2108.04539v5","paper_title":"BROS: A Pre-trained Language Model Focusing on Text and Layout for Better Key Information Extraction from Documents","paper_date":"2021-08-10","code_links":[{"title":"clovaai/bros","url":"https://github.com/clovaai/bros"},{"title":"2024-MindSpore-1/Code2","url":"https://github.com/2024-MindSpore-1/Code2/tree/main/model-1/bros"}],"metrics_order":"[\"F1\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":8372,"task":"Relation Extraction","parent_task":null,"dataset":"FUNSD","model_name":"LayoutLMv2 large","metrics":{"F1":"70.57"},"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":8373,"task":"Relation Extraction","parent_task":null,"dataset":"FUNSD","model_name":"LayoutLM","metrics":{"F1":"42.83"},"paper_url":"https://arxiv.org/abs/1912.13318v5","paper_title":"LayoutLM: Pre-training of Text and Layout for Document Image Understanding","paper_date":"2019-12-31","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":"microsoft/unilm","url":"https://github.com/microsoft/unilm/tree/master/layoutlm"},{"title":"PaddlePaddle/PaddleNLP","url":"https://github.com/PaddlePaddle/PaddleNLP/tree/develop/paddlenlp/transformers/layoutlm"},{"title":"impira/docquery","url":"https://github.com/impira/docquery"},{"title":"doc-analysis/DocBank","url":"https://github.com/doc-analysis/DocBank"},{"title":"BordiaS/layoutlm","url":"https://github.com/BordiaS/layoutlm"},{"title":"facebookresearch/data2vec_vision","url":"https://github.com/facebookresearch/data2vec_vision"},{"title":"omarsou/layoutlm_CORD","url":"https://github.com/omarsou/layoutlm_CORD"},{"title":"cydal/LayoutML_pytorch","url":"https://github.com/cydal/LayoutML_pytorch"},{"title":"lulia0228/Document_IE","url":"https://github.com/lulia0228/Document_IE"},{"title":"kenAlparslan/Texttract","url":"https://github.com/kenAlparslan/Texttract"},{"title":"thibaultdouzon/long-range-document-transformer","url":"https://github.com/thibaultdouzon/long-range-document-transformer"},{"title":"nunenuh/layoutlm.pytorch","url":"https://github.com/nunenuh/layoutlm.pytorch"},{"title":"pwc-1/Paper-9","url":"https://github.com/pwc-1/Paper-9/tree/main/layoutlm"},{"title":"yangyucheng000/papercode-2","url":"https://github.com/yangyucheng000/papercode-2/tree/main/layout-diffusion-mindspore"},{"title":"MS-P3/code3","url":"https://github.com/MS-P3/code3/tree/main/layoutlm"},{"title":"MindSpore-scientific-2/code-14","url":"https://github.com/MindSpore-scientific-2/code-14/tree/main/layoutlm"}],"metrics_order":"[\"F1\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]}]}