Structure-Preserving Extraction of Tabular Data from Engineering Manuals

• Vinícius A. Aguiar UFG / CEIA
• Gustavo L. B. Pereira UFG / CEIA
• Joao Pedro Gomes Fernandes UFG / CEIA
• Artur M. A. Novais UFG / CEIA
• Thiago Pedroso de Jesus UFG / CEIA
• Sávio S. T. de Oliveira UFG / CEIA
• Anderson S. Soares UFG / CEIA

DOI: https://doi.org/10.5753/eniac.2026.31336

Resumo

Engineering manuals encode operational parameters in dense tables, scanned pages, hierarchical sections, and multi-page layouts. Conventional OCR and layout conversion pipelines often flatten these structures, weakening the association between parameters, values, and document context. This work proposes a structure-preserving extraction pipeline that uses multimodal page parsing, explicit semantic tags, deterministic validation, and row-level context injection to convert heterogeneous manuals into structured tabular records. On 60 pages from six protection-relay manuals, the pipeline produced usable output for allevaluated pages, identified 04 structured tables, assigned 197 captions, and reconstructed 26 multi-page tables. The evaluation focuses on extraction and structural preservation and does not assess end-to-end question answering or SQL execution.

Referências

Blecher, L., Cucurull, G., Scialom, T., and Stojnic, R. (2023). Nougat: Neural optical understanding for academic documents. arXiv preprint arXiv:2308.13418.

Hong, T., Kim, D., Ji, M., Hwang, W., Nam, D., and Park, S. (2022). BROS: A pre-trained language model focusing on text and layout for better key information extraction from documents. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 36, pages 10767–10775.

Horowitz, S. H., Phadke, A. G., and Henville, C. F. (2022). Power system relaying. John Wiley & Sons, 5 edition.

Huang, Y., Lv, T., Cui, L., Lu, Y., and Wei, F. (2022). LayoutLMv3: Pre-training for document AI with unified text and image masking. In Proceedings of the 30th ACM international conference on multimedia, pages 4083–4091.

Kim, G., Hong, T., Yim, M., Nam, J., Park, J., Yim, J., Hwang, W., Yun, S., Han, D., and Park, S. (2022). OCR-free document understanding transformer. In European Conference on Computer Vision, pages 498–517. Springer.

Lewis, P., Perez, E., Piktus, A., Petroni, F., Karpukhin, V., Goyal, N., Küttler, H., Lewis, M., Yih, W.-t., Rocktäschel, T., et al. (2020). Retrieval-augmented generation for knowledge-intensive NLP tasks. Advances in neural information processing systems, 33:9459–9474.

Li, J., Xu, Y., Cui, L., and Wei, F. (2022). MarkupLM: Pre-training of text and markup language for visually rich document understanding. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 6078–6087.

Livathinos, N., Auer, C., Lysak, M., Nassar, A., Dolfi, M., Vagenas, P., Ramis, C. B., Omenetti, M., Dinkla, K., Kim, Y., et al. (2025). Docling: An efficient open-source toolkit for AI-driven document conversion. arXiv preprint arXiv:2501.17887.

Phadke, A. G. and Thorp, J. S. (2008). Synchronized phasor measurements and their applications, volume 1. Springer.

Schreiber, S., Agne, S., Wolf, I., Dengel, A., and Ahmed, S. (2017). DeepDeSRT: Deep learning for detection and structure recognition of tables in document images. In 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), volume 01, pages 1162–1167.

Smock, B., Pesala, R., and Abraham, R. (2022). PubTables-1M: Towards comprehensive table extraction from unstructured documents. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 4624–4632.

Souza, E., da Silva, P. F., Gomes, D., Batista, V., Batista, E., and Pacheco, M. (2024). TableRAG: A novel approach for augmenting llms with information from retrieved tables. In Proceedings of the 15th Brazilian Symposium in Information and Human Language Technology, pages 182–191.

Terzija, V., Valverde, G., Cai, D., Regulski, P., Madani, V., Fitch, J., Skok, S., Begovic, M. M., and Phadke, A. (2011). Wide-area monitoring, protection, and control of future electric power networks. Proceedings of the IEEE, 99(1):80–93.

Yu, X., Jian, P., and Chen, C. (2025). TableRAG: A retrieval augmented generation framework for heterogeneous document reasoning. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 14074–14093.

Zheng, X., Burdick, D., Popa, L., Zhong, X., and Wang, N. X. R. (2021). Global table extractor (GTE): A framework for joint table identification and cell structure recognition using visual context. In Proceedings of the IEEE/CVF winter conference on applications of computer vision, pages 697–706.

Zhong, V., Xiong, C., and Socher, R. (2017). Seq2SQL: Generating structured queries from natural language using reinforcement learning. CoRR, abs/1709.00103.

Zhong, X., ShafieiBavani, E., and Jimeno-Yepes, A. (2020). Image-based table recognition: data, model, and evaluation. In Computer Vision – ECCV 2020, volume 12366 of Lecture Notes in Computer Science, pages 564–580. Springer.