Elamur Research⌕
☰
home / papers / 2026 / An Open-Resource Knowledge Augmentation for Biomedical Lay Summarization

An Open-Resource Knowledge Augmentation for Biomedical Lay Summarization

Paper · 2026 · João Pedro Veloso and Evelin Amorim

Summary

The paper addresses biomedical lay summarization, which turns specialist research into text that non-experts can follow. Strong prior systems add external knowledge from UMLS. UMLS requires registration and licence renewal, and its licence forbids sharing derived data, which hurts reproducibility and excludes smaller teams. The authors present OpenBioLaySumm, which uses only open resources. YAKE! extracts keywords from each abstract. These keywords are looked up in DBpedia, and a classifier keeps only the biomedical candidates. The remaining concepts are linked into a per-document graph using cosine similarity. That graph is combined with the abstract text in the doc-enhance encoder-decoder architecture of Goldsack et al. (2023). On a subset of the eLife dataset, the open pipeline scores slightly below a reproduced UMLS-based system, reaching about 97% of its ROUGE-1. A manual check of the extracted keywords tested whether they capture each paper's central medical content. The work shows that a general-domain open knowledge base can largely replace a licensed ontology. This makes knowledge-augmented lay summarization easier to share and reproduce.

Key points

  • On eLife, OpenBioLaySumm scored ROUGE-1 58.44 and ROUGE-L 43.45, against 60.26 and 45.45 for the UMLS-based method.
  • The comparison covered four systems: fine-tuned BART, BART with YAKE! keywords appended to the input, a reproduction of Goldsack et al. (2023), and OpenBioLaySumm.
  • The DBpedia Lookup API returns up to 100 candidate entities per document, and non-biomedical entries are filtered out before the graph is built.
  • The UMLS baseline uses QuickUMLS instead of MetaMap, because the MetaMap NLP Content View was discontinued in the UMLS 2025AB release.
  • For RQ1, the authors manually assessed 500 keywords (10 per document), and the code is released publicly (github.com/evelinamorim/openbiolaysumm).

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

 Institutions

🔬INESC TECPorto · Portugal11 works · 1,180 citations

 Fields, topics and concepts

📚 Shelves 6The field of science this work belongs to (OpenAlex fields).Computer Science · 16,667 worksArtificial Intelligence · 16,194 worksArts and Humanities · 16,039 worksLanguage and Linguistics · 15,891 worksBiochemistry, Genetics and Molecular Biology · 234 worksMolecular Biology · 231 works

🧭 Topics 1Research subjects and languages the work is about.Summarization · 232 works

Cite

Cite as João Pedro Veloso and Evelin Amorim. 2026. An Open-Resource Knowledge Augmentation for Biomedical Lay Summarization. Proceedings of the Third Workshop on Patient-Oriented Language Processing (CL4Health) @ LREC 2026.

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.63317/3tu5fbwrdd3x

@inproceedings{veloso2026open,
  title = {{An Open-Resource Knowledge Augmentation for Biomedical Lay Summarization}},
  author = {João Pedro Veloso and Evelin Amorim},
  booktitle = {Proceedings of the Third Workshop on Patient-Oriented Language Processing (CL4Health) @ LREC 2026},
  year = {2026},
  doi = {10.63317/3tu5fbwrdd3x},
  url = {https://doi.org/10.63317/3tu5fbwrdd3x}
}

References

20 references, 5 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Iz Beltagy, Kyle Lo, and Arman Cohan. 2019. Scibert: A pretrained language model for scientific text. arXiv preprint arXiv:1903.10676.
  2. Carly M Goldstein and Rebecca A Krukowski. 2023. The importance of lay summaries for improving science communication. Annals of Behavioral Medicine, 57(7):509–510. find
  3. Iz Beltagy, Matthew E Peters, and Arman Cohan. 2020. Longformer: The long-document transformer. arXiv preprint arXiv:2004.05150.
  4. Xiaoli Huang, Jimmy Lin, and Dina Demner-Fushman. 2006. Evaluation of pico as a knowledge representation for clinical questions. In AMIA annual symposium proceedings, volume 2006, page 359. find
  5. Souramita Bhowmik, Anupam Jamatia, Dwijen Rudrapal, and Kunal Chakma. 2025. Biomedical lay summarization: Research progress and challenges. In 2025 3rd International Conference on Intelligent Systems, Advanced Computing and Communication (ISACC), pages 464–471. IEEE. find
  6. Esther Landhuis. 2016. Scientific literature: Information overload. Nature, 535(7612):457–458. find
  7. Lutz Bornmann and Rüdiger Mutz. 2015. Growth rates of modern science: A bibliometric analysis based on the number of publications and cited references. J. Assoc. Inf. Sci. Technol., 66(11):2215–2222. find
  8. Mike Lewis, Yinhan Liu, Naman Goyal, Marjan Ghazvininejad, Abdelrahman Mohamed, Omer Levy, Veselin Stoyanov, and Luke Zettlemoyer. 2020. Bart: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. In Proceedings of the 58th annual meeting of the…
  9. Ricardo Campos, Vítor Mangaravite, Arian Pasquali, Alípio Jorge, Célia Nunes, and Adam Jatowt. 2020. Yake! keyword extraction from single documents using multiple local features. Information Sciences, 509:257–289. find
  10. Kyle Lo, Lucy Lu Wang, Mark Neumann, Rodney Kinney, and Daniel S Weld. 2020. S2orc: The semantic scholar open research corpus. In Proceedings of the 58th annual meeting of the association for computational linguistics, pages 4969– 4983.
  11. Andrea Chaves, Cyrille Kesiku, and Begonya Garcia-Zapirain. 2022. Automatic Text Summarization of Biomedical Text Data: A Systematic Review. Information, 13(8):393. Number: 8 Publisher: Multidisciplinary Digital Publishing Institute. find
  12. Zheheng Luo, Qianqian Xie, and Sophia Ananiadou. 2023. Readability Controllable Biomedical Document Summarization. ArXiv:2210.04705 [cs]. find
  13. Luca Soldaini and Nazli Goharian. 2016. Quickumls: a fast, unsupervised approach for medical concept extraction. In MedIR workshop, sigir, pages 1–4. find
  14. Chen Tang, Shun Wang, Tomas Goldsack, and Chenghua Lin. 2023. Improving biomedical abstractive summarisation with knowledge aggregation from citation papers. arXiv preprint arXiv:2310.15684. find
  15. Lucy Lu Wang, Kyle Lo, Yoganand Chandrasekhar, Russell Reas, Jiangjiang Yang, Doug Burdick, Darrin Eide, Kathryn Funk, Yannis Katsis, Rodney Michael Kinney, et al. 2020. Cord-19: The covid-19 open research dataset. In Proceedings of the 1st Workshop on NLP for COVID-19 at ACL 2020.
  16. Mengqian Wang, Manhua Wang, Fei Yu, Yue Yang, Jennifer Walker, and Javed Mostafa. 2021. A systematic review of automatic text summarization for biomedical literature and EHRs. Journal of the American Medical Informatics Association : JAMIA, 28(10):2287–2297. find
  17. Chenghao Xiao, Kun Zhao, Xiao Wang, Siwei Wu, Sixing Yan, Tomas Goldsack, Sophia Ananiadou, Noura Al Moubayed, Liang Zhan, William K Cheung, et al. 2025. Overview of the biolaysumm 2025 shared task on lay summarization of biomedical research articles and radiology reports. In Proceedings of the 24th… find
  18. Qianqian Xie, Jennifer Amy Bishop, Prayag Tiwari, and Sophia Ananiadou. 2022. Pre-trained language models with domain knowledge for biomedical extractive summarization. Knowledge-Based Systems, 252:109460. find
  19. Qianqian Xie, Zheheng Luo, Benyou Wang, and Sophia Ananiadou. 2023. A Survey for Biomedical Text Summarization: From Pre-trained to Large Language Models. ArXiv:2304.08763 [cs]. — [arXiv:2304.08763](https://arxiv.org/abs/2304.08763) find
  20. Qianqian Xie, Prayag Tiwari, and Sophia Ananiadou. 2024. Knowledge-Enhanced Graph Topic Transformer for Explainable Biomedical Text Summarization. IEEE Journal of Biomedical and Health Informatics, 28(4):1836–1847. find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/veloso-2026-open-resource-knowledge-augmentation-biomedical/