Scholarlink

Industrial projects rely heavily on lengthy, complex 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, which 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% accuracy and GPT-3.5 Turbo reaching 89% accuracy 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.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Automating Table of Contents Structuring: Leveraging GPT-3.5 and Donut for Efficient Document Indexing

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Degaga Wolde Feyisa,
  • Amanuel Zewdu,
  • Haylemicheal Berihun,
  • Marzieh Zare,
  • Mahsa Najimoghadam

摘要

Industrial projects rely heavily on lengthy, complex 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, which 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% accuracy and GPT-3.5 Turbo reaching 89% accuracy 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.