Layout Xlm Base Finetuned With DocLayNet Base At Linelevel Ml384

🚀 文档理解模型（在DocLayNet基础数据集上按行级别微调的LayoutXLM基础模型）

该模型是一个文档理解模型，基于microsoft/layoutxlm-base，使用DocLayNet base数据集进行微调。它在文档布局分析和理解方面表现出色，能为各类文档提供准确的结构识别和内容分类。

🚀 快速开始

本模型可用于文档理解任务，特别是在文档布局分析和行级别的文本分类方面。你可以通过以下资源快速上手：

• 推理：参考笔记本 Document AI | Inference at line level with a Document Understanding model (LayoutXLM base fine-tuned on DocLayNet dataset)。
• 训练和评估：参考笔记本 Document AI | Fine-tune LayoutXLM base on DocLayNet base in any language at line level (chunk of 384 tokens with overlap)。

✨ 主要特性

• 多语言支持：支持多种语言，适用于不同语言环境下的文档理解。
• 高精度：在评估集上取得了良好的指标，如F1值达到0.7336，准确率达到0.9373。
• 行级处理：模型在384个标记的块上按行级别进行微调，能够对每行文本进行准确分类。

📚 详细文档

模型描述

该模型在384个标记的块上按行级别进行微调，重叠128个标记。因此，模型使用了数据集中所有页面的布局和文本数据进行训练。在推理时，通过计算最佳概率为每个行边界框分配标签。

推理

你可以参考以下笔记本进行推理：Document AI | Inference at line level with a Document Understanding model (LayoutXLM base fine-tuned on DocLayNet dataset)。

训练和评估数据

关于训练和评估数据的详细信息，请参考笔记本：Document AI | Fine-tune LayoutXLM base on DocLayNet base in any language at line level (chunk of 384 tokens with overlap)。

训练过程

训练超参数

训练过程中使用了以下超参数：

训练结果

框架版本

• Transformers 4.26.1
• Pytorch 1.10.0+cu111
• Datasets 2.10.1
• Tokenizers 0.13.2

参考资料

博客文章

• Layout XLM base
  • (03/05/2023) Document AI | Inference APP and fine-tuning notebook for Document Understanding at line level with LayoutXLM base
• LiLT base
  • (02/16/2023) Document AI | Inference APP and fine-tuning notebook for Document Understanding at paragraph level
  • (02/14/2023) Document AI | Inference APP for Document Understanding at line level
  • (02/10/2023) Document AI | Document Understanding model at line level with LiLT, Tesseract and DocLayNet dataset
  • (01/31/2023) Document AI | DocLayNet image viewer APP
  • (01/27/2023) Document AI | Processing of DocLayNet dataset to be used by layout models of the Hugging Face hub (finetuning, inference)

笔记本（段落级别）

• LiLT base
  • Document AI | Inference APP at paragraph level with a Document Understanding model (LiLT fine-tuned on DocLayNet dataset)
  • Document AI | Inference at paragraph level with a Document Understanding model (LiLT fine-tuned on DocLayNet dataset)
  • Document AI | Fine-tune LiLT on DocLayNet base in any language at paragraph level (chunk of 512 tokens with overlap)

笔记本（行级别）

• Layout XLM base
  • Document AI | Inference at line level with a Document Understanding model (LayoutXLM base fine-tuned on DocLayNet dataset)
  • Document AI | Inference APP at line level with a Document Understanding model (LayoutXLM base fine-tuned on DocLayNet base dataset)
  • Document AI | Fine-tune LayoutXLM base on DocLayNet base in any language at line level (chunk of 384 tokens with overlap)
• LiLT base
  • Document AI | Inference at line level with a Document Understanding model (LiLT fine-tuned on DocLayNet dataset)
  • Document AI | Inference APP at line level with a Document Understanding model (LiLT fine-tuned on DocLayNet dataset)
  • Document AI | Fine-tune LiLT on DocLayNet base in any language at line level (chunk of 384 tokens with overlap)
  • DocLayNet image viewer APP
  • Processing of DocLayNet dataset to be used by layout models of the Hugging Face hub (finetuning, inference)

APP

你可以使用Hugging Face Spaces中的这个应用程序测试该模型：Inference APP for Document Understanding at line level (v2)。

DocLayNet数据集

DocLayNet数据集（IBM）为来自6个文档类别的80863个唯一页面上的11个不同类别标签提供了逐页布局分割的真实标注，使用了边界框。到目前为止，该数据集可以通过直接链接或从Hugging Face数据集下载：

• 直接链接：doclaynet_core.zip（28 GiB），doclaynet_extra.zip（7.5 GiB）
• Hugging Face数据集库：dataset DocLayNet

论文：DocLayNet: A Large Human-Annotated Dataset for Document-Layout Analysis（06/02/2022）

其他模型

• 行级别
  • Document Understanding model (finetuned LiLT base at line level on DocLayNet base)（准确率 | 标记：85.84% - 行：91.97%）
  • Document Understanding model (finetuned LayoutXLM base at line level on DocLayNet base)（准确率 | 标记：93.73% - 行：...）
• 段落级别
  • Document Understanding model (finetuned LiLT base at paragraph level on DocLayNet base)（准确率 | 标记：86.34% - 段落：68.15%）
  • Document Understanding model (finetuned LayoutXLM base at paragraph level on DocLayNet base)（准确率 | 标记：96.93% - 段落：86.55%）

📄 许可证

本模型采用MIT许可证。