Elamur Research⌕
☰
home / papers / 2026 / Enhancing Scholarly Knowledge Graphs via Domain-Specific Entity Detection and Linking

Enhancing Scholarly Knowledge Graphs via Domain-Specific Entity Detection and Linking

Paper · 2026 · Nicolau Duran-Silva, César A. Parra-Rojas, Pablo Accuosto et al.

Summary

Scholarly knowledge graphs (SKGs) connect publications, datasets and software. Enriching them with fine-grained, field-specific concepts is difficult because most scientific areas lack annotated data for named-entity recognition (NER) and entity linking (EL), and expert labelling is costly. Within the EU SciLake project, the authors build a pipeline meant to transfer across fields and apply it to four pilot communities: Neuroscience, Energy, Maritime Transport and CCAM.

The pipeline works in stages. An LLM first drafts pseudo-labels on full-text paper sections segmented with GROBID. Domain experts then check these labels in a human-in-the-loop step. The validated data is used to fine-tune transformer NER models and few-shot GLiNER models. Detected mentions are then mapped to domain taxonomies through a retrieve-and-rerank EL stage, which uses an E5 retriever and a Qwen reranker and adds LLM-written mention descriptions in the spirit of LLMAEL.

The evaluation sections were missing from the supplied text, so no headline scores are given here. The contribution is a reusable way to cover entity types absent from existing NER datasets with reduced annotation effort. Code, models and data are released openly.

Key points

  • Corpus: 1,000 full-text papers (Neuroscience, Transport, Energy, Cancer) plus 1,000 random general-science papers, split into sections with GROBID.
  • Entity types and knowledge bases:
    • Neuroscience has 5 types (technique, preparation type, parcellation, species, biological sex), linked to openMINDS and UBERON (restricted to the central nervous system).
    • Energy has 2 types (energy type, energy storage), linked to IRENA.
    • Maritime has 1 type (vessel type), linked to AIS ship classes.
    • CCAM has 7 types (e.g., VRU type, sensor type, level of automation), linked to subsets of SINFONICA and FAME.
  • Annotation prompt rules: the LLM must copy spans exactly, handle acronyms carefully, and skip any entity without explicit textual support.
  • Training setup:
    • NER: AdamW, lr 2e-5, batch size 16, 6 epochs.
    • GLiNER: focal loss, lr 5e-6, prediction threshold 0.5.
    • E5 retriever: MNRLoss, 10 TF–IDF hard negatives, 3 epochs.
    • Hardware: all models trained on a single NVIDIA A100.
    • Context augmentation: 2–3 few-shot examples per domain.
  • Resources: released at github.com/sirisacademic/meloner. Note that the introduction mentions "five pilot domains" but lists only four.

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

🔬German Research Centre for Artificial IntelligenceKaiserslautern · Germany79 works · 29,970 citations🎓Universitat Pompeu FabraBarcelona · Spain48 works · 12,092 citations🏢SIRIS AcademicBarcelona · Spain2 works

 Fields, topics and concepts

📚 Shelves 6The field of science this work belongs to (OpenAlex fields).Computer Science · 18,614 worksArtificial Intelligence · 17,965 worksArts and Humanities · 17,450 worksLanguage and Linguistics · 17,296 worksBiochemistry, Genetics and Molecular Biology · 263 worksMolecular Biology · 260 works

🧭 Topics 1Research subjects and languages the work is about.Knowledge graphs & ontologies · 211 works

Cite

Cite as Nicolau Duran-Silva, César A. Parra-Rojas, Pablo Accuosto, Julian Moreno-Schneider and Georg Rehm. 2026. Enhancing Scholarly Knowledge Graphs via Domain-Specific Entity Detection and Linking. Proceedings of Natural Scientific Language Processing (NSLP) @ LREC 2026.

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.63317/43szrv2r8njb

@inproceedings{duransilva2026enhancing,
  title = {{Enhancing Scholarly Knowledge Graphs via Domain-Specific Entity Detection and Linking}},
  author = {Nicolau Duran-Silva, César A. Parra-Rojas, Pablo Accuosto, Julian Moreno-Schneider and Georg Rehm},
  booktitle = {Proceedings of Natural Scientific Language Processing (NSLP) @ LREC 2026},
  year = {2026},
  doi = {10.63317/43szrv2r8njb},
  url = {https://doi.org/10.63317/43szrv2r8njb}
}

References

54 references, 11 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Tom Ayoola, Shubhi Tyagi, Joseph Fisher, Christos Christodoulopoulos, and Andrea Pierleoni. 2022. Refined: An efficient zero-shot-capable approach to end-to-end entity linking. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human… find
  2. Iz Beltagy, Kyle Lo, and Arman Cohan. 2019. SciB-ERT: A pretrained language model for scientific text. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 3615–3620,… find
  3. Nicola De Cao, Gautier Izacard, Sebastian Riedel, and Fabio Petroni. 2021. Autoregressive entity retrieval. find
  4. Dalmeet Singh Chawla. 2017. Unpaywall finds free versions of paywalled papers. Nature. find
  5. Jianlyu Chen, Shitao Xiao, Peitian Zhang, Kun Luo, Defu Lian, and Zheng Liu. 2024. M3-embedding: Multi-linguality, multi-functionality, multi-granularity text embeddings through self-knowledge distillation. In Findings of the Association for Computational Linguistics: ACL 2024, pages 2318–2335, Bang…
  6. Arman Cohan, Sergey Feldman, Iz Beltagy, Doug Downey, and Daniel S. Weld. 2020. Specter: Document-level representation learning using citation-informed transformers.
  7. Vila-Suero Daniel and Aranda Francisco. 2023. Argilla - Open-source framework for data-centric NLP. find
  8. Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies,…
  9. Carol Friedman, Pauline Kra, and Andrey Rzhetsky. 2002. Two biomedical sublanguages: a description based on the theories of zellig harris. Journal of biomedical informatics, 35(4):222–235. find
  10. Suchin Gururangan, Ana Marasović, Swabha Swayamdipta, Kyle Lo, Iz Beltagy, Doug Downey, and Noah A. Smith. 2020. Don’t stop pretraining: Adapt language models to domains and tasks. In Proceedings of ACL. find
  11. Yun He, Ziwei Zhu, Yin Zhang, Qin Chen, and James Caverlee. 2020. Infusing Disease Knowledge into BERT for Health Question Answering, Medical Inference and Disease Name Recognition. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 4604–4614, On… find
  12. Ginny Hendricks, Dominika Tkaczyk, Jennifer Lin, and Patricia Feeney. 2020. Crossref: The sustainable source of community-owned scholarly metadata. Quantitative Science Studies, 1(1):414–427. find
  13. Zhi Hong, Aswathy Ajith, Gregory Pauloski, Eamon Duede, Carl Malamud, Roger Magoulas, Kyle Chard, and Ian T. Foster. 2022. Scholarbert: Bigger is not always better. ArXiv, abs/2205.11342. — [arXiv:2205.11342](https://arxiv.org/abs/2205.11342) find
  14. Zhi Hong, Roselyne Tchoua, Kyle Chard, and Ian Foster. 2020. Sciner: extracting named entities from scientific literature. In International Conference on Computational Science, pages 308–321. Springer. find
  15. Mohamad Yaser Jaradeh, Allard Oelen, Kheir Eddine Farfar, Manuel Prinz, Jennifer D’Souza, Gábor Kismihók, Markus Stocker, and Sören Auer. 2019. Open research knowledge graph: Next generation infrastructure for semantic scholarly knowledge. In Proceedings of the 10th international conference on knowl… find
  16. Jin-Dong Kim, Yue Wang, Toshihisa Takagi, and Akinori Yonezawa. 2011. Overview of genia event task in bionlp shared task 2011. In Proceedings of BioNLP shared task 2011 workshop, pages 7–15. find
  17. Jeremy Leipzig, Daniel Nüst, Charles Tapley Hoyt, Karthik Ram, and Jane Greenberg. 2021. The role of metadata in reproducible computational research. Patterns, 2(9):100322. find
  18. Jiao Li, Yueping Sun, Robin J Johnson, Daniela Sciaky, Chih-Hsuan Wei, Robert Leaman, Allan Peter Davis, Carolyn J Mattingly, Thomas C Wiegers, and Zhiyong Lu. 2016. Biocreative v cdr task corpus: a resource for chemical disease relation extraction. find
  19. Mingchen Li and Rui Zhang. 2023. How far is language model from 100% few-shot named entity recognition in medical domain. arXiv preprint arXiv:2307.00186. find
  20. Fangyu Liu, Ehsan Shareghi, Zaiqiao Meng, Marco Basaldella, and Nigel Collier. 2021. Self-alignment pretraining for biomedical entity representations. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pa…
  21. Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. 2019. Roberta: A robustly optimized bert pre-training approach. find
  22. Yiren Liu, Si Chen, Haocong Cheng, Mengxia Yu, Xiao Ran, Andrew Mo, Yiliu Tang, and Yun Huang. 2024. How ai processing delays foster creativity: Exploring research question co-creation with an llm-based agent. In Proceedings of the 2024 CHI Conference on Human Factors in Computing Systems, CHI ’24,… find
  23. Patrice Lopez. 2009. Grobid: Combining automatic bibliographic data recognition and term extraction for scholarship publications. In International conference on theory and practice of digital libraries, pages 473–474. Springer. find
  24. Yi Luan, Luheng He, Mari Ostendorf, and Hannaneh Hajishirzi. 2018. Multi-task identification of entities, relations, and coreference for scientific knowledge graph construction. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 3219– 3232, Brussels, Bel…
  25. Ling Luo, Chih-Hsuan Wei, Po-Ting Lai, Robert Leaman, Qingyu Chen, and Zhiyong Lu. 2023. Aioner: all-in-one scheme-based biomedical named entity recognition using deep learning. Bioinformatics, 39(5):btad310. find
  26. Paolo Manghi. 2024. Challenges in building scholarly knowledge graphs for research assessment in open science. Quantitative Science Studies, 5(4):991–1021. find
  27. Paolo Manghi, Alessia Bardi, Claudio Atzori, Miriam Baglioni, Natalia Manola, Jochen Schirrwagen, Pedro Principe, Michele Artini, Amelie Becker, Michele De Bonis, et al. 2019. The openaire research graph data model. Zenodo. find
  28. Rada Mihalcea and Andras Csomai. 2007. Wikify! linking documents to encyclopedic knowledge. In Proceedings of the Sixteenth ACM Conference on Conference on Information and Knowledge Management, CIKM ’07, page 233–242, New York, NY, USA. Association for Computing Machinery. find
  29. Faizan E Mustafa, Corina Dima, Juan Ochoa, and Steffen Staab. 2024. Leveraging Wikidata for biomedical entity linking in a low-resource setting: A case study for German. In Proceedings of the 6th Clinical Natural Language Processing Workshop, pages 202–207, Mexico City, Mexico. Association for Compu… find
  30. Cameron Neylon, Bianca Kramer, Alysson Fernandes Mazoni, Rodrigo Costas, Najko Jahn, and Nees Jan van Eck. 2026. Sharing the load: Building a collective to support open research information online. Upstream. find
  31. Marc Pàmies, Joan Llop, Francesco Multari, Nicolau Duran-Silva, César Parra-Rojas, Aitor Gonzalez-Agirre, Francesco Alessandro Massucci, and Marta Villegas. 2023. A weakly supervised textual entailment approach to zero-shot text classification. In Proceedings of the 17th Conference of the European C… find
  32. Silvio Peroni and David Shotton. 2020. Opencitations, an infrastructure organization for open scholarship. Quantitative Science Studies, 1(1):428–444. find
  33. Jason Priem, Heather A. Piwowar, and Richard Orr. 2022. Openalex: A fully-open index of scholarly works, authors, venues, institutions, and concepts. ArXiv, abs/2205.01833. — [arXiv:2205.01833](https://arxiv.org/abs/2205.01833) find
  34. Nils Reimers and Iryna Gurevych. 2019. Sentence-BERT: Sentence embeddings using Siamese BERT-networks. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 3982–3992,…
  35. Wei Liang Seow, Iti Chaturvedi, Amber Hogarth, Rui Mao, and Erik Cambria. 2025. A review of named entity recognition: from learning methods to modelling paradigms and tasks. Artificial Intelligence Review, 58(10):315. find
  36. Darya Shlyk, Tudor Groza, Marco Mesiti, Stefano Montanelli, and Emanuele Cavalleri. 2024. REAL: A retrieval-augmented entity linking approach for biomedical concept recognition. In Proceedings of the 23rd Workshop on Biomedical Natural Language Processing, pages 380– 389, Bangkok, Thailand. Associat… find
  37. Amanpreet Singh, Mike D’Arcy, Arman Cohan, Doug Downey, and Sergey Feldman. 2022. Scirepeval: A multi-format benchmark for scientific document representations. In Conference on Empirical Methods in Natural Language Processing. find
  38. Saba Sturua, Isabelle Mohr, Mohammad Kalim Akram, Michael Günther, Bo Wang, Markus Krimmel, Feng Wang, Georgios Mastrapas, Andreas Koukounas, Andreas Koukounas, Nan Wang, and Han Xiao. 2024. jina-embeddings-v3: Multilingual embeddings with task lora.
  39. Sina Taslimi, Artemis Capari, Hosein Azarbonyad, Zi Long Zhu, Zubair Afzal, Evangelos Kanoulas, and George Tsatsaronis. 2025. Extracting, detecting, and generating research questions for scientific articles. In Proceedings of the 31st International Conference on Computational Linguistics, pages 8573… find
  40. Qwen Team. 2025. Qwen3 technical report. find
  41. Thanasis Vergoulis, Serafeim Chatzopoulos, Ilias Kanellos, Panagiotis Deligiannis, Christos Try-fonopoulos, and Theodore Dalamagas. 2019. Bip! finder: Facilitating scientific literature search by exploiting impact-based ranking. In Proceedings of the 28th ACM international conference on information… find
  42. Feng Wang, Yuqing Li, and Han Xiao. 2025. jina-reranker-v3: Last but not late interaction for document reranking. find
  43. Liang Wang, Nan Yang, Xiaolong Huang, Linjun Yang, Rangan Majumder, and Furu Wei. 2024. Multilingual e5 text embeddings: A technical report. arXiv preprint arXiv:2402.05672.
  44. Max Wilkinson. 2010. Datacite: The international data citation initiative: Datasets programme. find
  45. Ledell Wu, Fabio Petroni, Martin Josifoski, Sebastian Riedel, and Luke Zettlemoyer. 2020a. Scalable zero-shot entity linking with dense entity retrieval. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 6397–6407, Online. Association for Comput…
  46. Ledell Wu, Fabio Petroni, Martin Josifoski, Sebastian Riedel, and Luke Zettlemoyer. 2020b. Scalable zero-shot entity linking with dense entity retrieval. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 6397–6407, Online. Association for Comput…
  47. Mingfang Wu, Felicitas Löffler, Brigitte Mathiak, Fotis Psomopoulos, Uwe Schindler, Amir Aryani, Jordi Bodera Sempere, Antica Culina, Andreas Czerniak, Chris Erdmann, et al. 2026. Bridging the data discovery gap: User-centric recommendations for research data repositories. Data Science Journal, 25(6… find
  48. Zilin Xiao, Ming Gong, Jie Wu, Xingyao Zhang, Linjun Shou, and Daxin Jiang. 2023. Instructed language models with retrievers are powerful entity linkers. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 2267–2282, Singapore. Association for Computation… find
  49. Amy Xin, Yunjia Qi, Zijun Yao, Fangwei Zhu, Kaisheng Zeng, Bin Xu, Lei Hou, and Juanzi Li. 2025. Llmael: Large language models are good context augmenters for entity linking. In Proceedings of the 34th ACM International Conference on Information and Knowledge Management, pages 3550–3559. find
  50. Zhenran Xu, Yulin Chen, Baotian Hu, and Min Zhang. 2023. A read-and-select framework for zero-shot entity linking. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 13657–13666, Singapore. Association for Computational Linguistics. find
  51. Artur Yakimovich, Anaël Beaugnon, Yi Huang, and Elif Ozkirimli. 2021. Labels in a haystack: Approaches beyond supervised learning in biomedical applications. Patterns, 2(12):100383. find
  52. Anthony Yazdani, Ihor Stepanov, and Douglas Teodoro. 2025. Gliner-biomed: A suite of efficient models for open biomedical named entity recognition. arXiv preprint arXiv:2504.00676. — [arXiv:2504.00676](https://arxiv.org/abs/2504.00676) find
  53. Zheng Yuan, Yijia Liu, Chuanqi Tan, Songfang Huang, and Fei Huang. 2021. Improving biomedical pretrained language models with knowledge. In Proceedings of the 20th Workshop on Biomedical Language Processing, pages 180–190, Online. Association for Computational Linguistics. find
  54. Urchade Zaratiana, Nadi Tomeh, Pierre Holat, and Thierry Charnois. 2024. GLiNER: Generalist model for named entity recognition using bidirectional transformer. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technol…

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/silva-2026-enhancing-scholarly-knowledge-graphs-domain/