The future of document indexing: GPT and Donut revolutionize table of content processing
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913262363213824 |
|---|---|
| author | Feyisa, Degaga Wolde Berihun, Haylemicheal Zewdu, Amanuel Najimoghadam, Mahsa Zare, Marzieh |
| author_facet | Feyisa, Degaga Wolde Berihun, Haylemicheal Zewdu, Amanuel Najimoghadam, Mahsa Zare, Marzieh |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_07553 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | The future of document indexing: GPT and Donut revolutionize table of content processing Feyisa, Degaga Wolde Berihun, Haylemicheal Zewdu, Amanuel Najimoghadam, Mahsa Zare, Marzieh Information Retrieval Artificial Intelligence Computer Vision and Pattern Recognition 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. |
| title | The future of document indexing: GPT and Donut revolutionize table of content processing |
| topic | Information Retrieval Artificial Intelligence Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2403.07553 |