Industrial projects rely heavily on lengthy, complex specification documents,
making tedious manual extraction of structured information a major bottleneck.
This paper introduces an innovative approach to automate this process,
leveraging the capabilities of two cutting-edge AI models: Donut, a model that
extracts information directly from scanned documents without OCR, and OpenAI
GPT-3.5 Turbo, a robust large language model. The proposed methodology is
initiated by acquiring the table of contents (ToCs) from construction
specification documents and subsequently structuring the ToCs text into JSON
data. Remarkable accuracy is achieved, with Donut reaching 85% and GPT-3.5
Turbo reaching 89% in effectively organizing the ToCs. This landmark
achievement represents a significant leap forward in document indexing,
demonstrating the immense potential of AI to automate information extraction
tasks across diverse document types, boosting efficiency and liberating
critical resources in various industries.

该论文介绍了一种创新方法，利用两个先进的 AI 模型 (Donut 和 OpenAI GPT-3.5 Turbo) 自动从复杂的规范文档中提取结构化信息，通过获取建筑规范文档的目录，将目录文本结构化为 JSON 数据，实现了卓越的准确性 (85% 对于 Donut，89% 对于 GPT-3.5 Turbo)，这一里程碑式的成就将文档索引带入了一个重要飞跃，展示了 AI 在不同类型文档中自动化信息提取任务上的巨大潜力，提高了效率，解放了各行各业的重要资源。

文档索引的未来：GPT 和 Donut 革新目录内容处理

The future of document indexing: GPT and Donut revolutionize table of  content processing

Understanding document images (e.g., invoices) is a core but challenging task
since it requires complex functions such as reading text and a holistic
understanding of the document. Current Visual Document Understanding (VDU)
methods outsource the task of reading text to off-the-shelf Optical Character
Recognition (OCR) engines and focus on the understanding task with the OCR
outputs. Although such OCR-based approaches have shown promising performance,
they suffer from 1) high computational costs for using OCR; 2) inflexibility of
OCR models on languages or types of document; 3) OCR error propagation to the
subsequent process. To address these issues, in this paper, we introduce a
novel OCR-free VDU model named Donut, which stands for Document understanding
transformer. As the first step in OCR-free VDU research, we propose a simple
architecture (i.e., Transformer) with a pre-training objective (i.e.,
cross-entropy loss). Donut is conceptually simple yet effective. Through
extensive experiments and analyses, we show a simple OCR-free VDU model, Donut,
achieves state-of-the-art performances on various VDU tasks in terms of both
speed and accuracy. In addition, we offer a synthetic data generator that helps
the model pre-training to be flexible in various languages and domains. The
code, trained model and synthetic data are available at
this https URL

本文介绍了一种名为 “Donut” 的 OCR-free VDU 模型，使用 Transformer 作为简单有效的架构对文档图像进行全面理解，并采用交叉熵损失预训练，通过实验表明该模型在速度和准确性方面达到了各种 VDU 任务的最新表现。