Elamur Research⌕
☰
home / papers / 2026 / ENEIDE: A High Quality Silver Standard Dataset for Named Entity Recognition and Linking in Historical Italian

ENEIDE: A High Quality Silver Standard Dataset for Named Entity Recognition and Linking in Historical Italian

Summary

Historical Italian has very few annotated resources for Named Entity Recognition and Linking (NERL). The only earlier dataset, MHERCL, covers just music periodicals and offers only a test split, so it cannot be used for training. ENEIDE fills this gap by converting expert entity markup from two Scholarly Digital Editions (SDEs) into a silver standard corpus. The sources are Digital Zibaldone, Giacomo Leopardi's 19th-century philosophical notebook, and Aldo Moro Digitale, the 20th-century writings of the politician Aldo Moro. The authors built a semi-automatic pipeline that converts TEI/XML-derived annotations, samples documents, checks quality and enriches sparse annotations. Entities are tied to Wikidata, and NIL marks entities with no match. This makes ENEIDE the first publicly available NERL corpus of historical Italian that spans multiple domains and is divided into separate training, development and test sets. Baseline tests show a clear gap between zero-shot systems and fine-tuned ones, and the literary partition is the hardest. The resource supports work on temporal disambiguation, cross-domain evaluation and the reuse of digital humanities editions as NLP training data.

Key points

  • The corpus contains 2,111 documents and more than 8,000 entity annotations. Entity types are person, location, organization and literary work, each linked to Wikidata identifiers or marked as NIL.
  • The two partitions are Digital Zibaldone (DZ), whose expert annotations were produced at Princeton, and Aldo Moro Digitale (AMD), whose annotations were enhanced semi-automatically with expert validation.
  • In the baselines, NER F1 ranges from 0.340 to 0.876 and EL accuracy from 0.502 to 0.689. The literary domain gives the lowest results.
  • Referenced entities range from classical antiquity (mostly in DZ) to mid-20th-century Italian politics (mostly in AMD).
  • The dataset is released on Zenodo (doi.org/10.5281/zenodo.17407356) under CC BY-NC-SA 4.0. Its known limitations are coverage of only two authors and minimal multilingual content, limited to some French, Latin and Greek in DZ.

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

Fields: Linguistics & languages

Topics: Named entity recognition

Cite

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.63317/3hwbiiv85eub

@inproceedings{santini2026eneide,
  title = {{ENEIDE: A High Quality Silver Standard Dataset for Named Entity Recognition and Linking in Historical Italian}},
  author = {Santini, Cristian and Barzaghi, Sebastian and Sernani, Paolo and Frontoni, Emanuele and Melosi, Laura and Alam, Mehwish},
  booktitle = {Proceedings of the Fifteenth Language Resources and Evaluation Conference},
  year = {2026},
  doi = {10.63317/3hwbiiv85eub},
  url = {https://doi.org/10.63317/3hwbiiv85eub}
}

References

29 references, 2 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Ben Adida, Mark Birbeck, Shane McCarron, and Ivan Herman. 2007. Rdfa core 1.1. find
  2. Prabal Agarwal, Jannik Strötgen, Luciano Del Corro, Johannes Hoffart, and Gerhard Weikum. 2018. dianed: Time-aware named entity disambiguation for diachronic corpora. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 686–693. find
  3. Mariona Coll Ardanuy, David Beavan, Kaspar Beelen, Kasra Hosseini, Jon Lawrence, Katherine McDonough, Federico Nanni, Daniel van Strien, and Daniel CS Wilson. 2022. A dataset for toponym resolution in nineteenth-century english newspapers. Journal of Open Humanities Data, 8. find
  4. David Bamman, Sejal Popat, and Sheng Shen. 2019. An annotated dataset of literary entities. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 2138–2144, Minneapoli… find
  5. Sebastian Barzaghi, Alessio Palmero Aprosio, Francesco Paolucci, Francesca Tomasi, Sara Tonelli, Marialaura Vignocchi, and Fabio Vitali. 2025. The semantic digital edition of aldo moro’s writings: A workflow supporting data sharing and replicability. J. Comput. Cult. Herit. find
  6. Giovanni Colavizza and Matteo Romanello. 2017. Annotated References in the Historiography on Venice: 19th–21st centuries. Journal of Open Humanities Data, 3:2–2. find
  7. Nicola De Cao, Ledell Wu, Kashyap Popat, Mikel Artetxe, Naman Goyal, Mikhail Plekhanov, Luke Zettlemoyer, Nicola Cancedda, Sebastian Riedel, and Fabio Petroni. 2022. Multilingual autoregressive entity linking. Transactions of the Association for Computational Linguistics, 10:274–290. find
  8. Maud Ehrmann, Ahmed Hamdi, Elvys Linhares Pontes, Matteo Romanello, and Antoine Doucet. 2023. Named entity recognition and classification in historical documents: A survey. ACM Comput. Surv., 56(2). find
  9. Maud Ehrmann, Matteo Romanello, Sven Najem-Meyer, Antoine Doucet, and Simon Clematide. 2022. Overview of hipe-2022: named entity recognition and linking in multilingual historical documents. In International Conference of the Cross-Language Evaluation Forum for European Languages, pages 423–446. Spr… find
  10. Arianna Graciotti, Leonardo Piano, Nicolas Lazzari, Enrico Daga, Rocco Tripodi, Valentina Presutti, and Livio Pompianu. 2025. Ke-mhisto: Towards a multilingual historical knowledge extraction benchmark for addressing the long-tail problem. In Proceedings of the 63rd Annual Meeting of the Association… find
  11. Samira Nabiafjadi, Maryam Sharifzadeh, and Mostafa Ahmadvand. 2021. Social network analysis for identifying actors engaged in water governance: An endorheic basin case in the middle east. Journal of Environmental Management, 288:112376. find
  12. Teresa Paccosi and Alessio Palmero Aprosio. 2022. KIND: an Italian multi-domain dataset for named entity recognition. In Proceedings of the Thirteenth Language Resources and Evaluation Conference, pages 501–507, Marseille, France. European Language Resources Association. find
  13. Mikhail Plekhanov, Nora Kassner, Kashyap Popat, Louis Martin, Simone Merello, Borislav Kozlovskii, Frédéric A Dreyer, and Nicola Cancedda. 2023. Multilingual end to end entity linking. arXiv preprint arXiv:2306.08896. — [arXiv:2306.08896](https://arxiv.org/abs/2306.08896) find
  14. Riccardo Pozzi, Riccardo Rubini, Christian Bernasconi, and Matteo Palmonari. 2023. Named entity recognition and linking for entity extraction from italian civil judgements. In International Conference of the Italian Association for Artificial Intelligence, pages 187–201. Springer. find
  15. Dietrich Rebholz-Schuhmann, Antonio José Jimeno Yepes, Erik M. van Mulligen, Ning Kang, Jan Kors, David Milward, Peter Corbett, Ekaterina Buyko, Katrin Tomanek, Elena Beisswanger, and Udo Hahn. 2010. The CALBC silver standard corpus for biomedical named entities — a study in harmonizing the contribu… find
  16. Matteo Romanello and Sven Najem-Meyer. 2024. A Named Entity-Annotated Corpus of 19th Century Classical Commentaries. Journal of Open Humanities Data, 10(1). find
  17. Patrick Sahle. 2016. What is a scholarly digital edition? Digital scholarly editing: Theories and practices, 1:19–39. Publisher: Open Book Publishers Cambridge. find
  18. Silvia Stoyanova. 2013. Fragmentary narrative and the formation of pre-digital scholarly hypertextuality: G. Leopardi’s Zibaldone and its hypertext rendition. In Proceedings of the 3rd Narrative and Hypertext Workshop, NHT ’13, pages 1–6, New York, NY, USA. Association for Computing Machinery. find
  19. Silvia Stoyanova. 2023. Working with the Digital Edition of Giacomo Leopardi’s Zibaldone. maga-zén, 4(3):13. find
  20. Silvia Stoyanova and Ben Johnston. 2014. Remediating Giacomo Leopardi’s Zibaldone: Hypertextual Semantic Networks in the Scholarly Archive. In Proceedings of the Third AIUCD Annual Conference on Humanities and Their Methods in the Digital Ecosystem, AIUCD ’14, pages 1–8, New York, NY, USA. Associati… find
  21. Mathieu Valette. 2024. What does perspectivism mean? an ethical and methodological countercriticism. In Proceedings of the 3rd Workshop on Perspectivist Approaches to NLP (NLPerspectives)@ LREC-COLING 2024, pages 111–115. find
  22. Denny Vrandečić and Markus Krötzsch. 2014. Wikidata: a free collaborative knowledgebase. Communications of the ACM, 57(10):78–85. find
  23. Christopher Walker, Stephanie Strassel, Julie Medero, and Kazuaki Maeda. 2006. find
  24. ACE 2005 Multilingual Training Corpus. Artwork Size: 1572864 KB Pages: 1572864 KB. find
  25. Lars Wissler, Mohammed Almashraee, Dagmar Monett Díaz, and Adrian Paschke. 2014. The gold standard in corpus annotation. IEEE GSC, 21. find
  26. Ledell Wu, Fabio Petroni, Martin Josifoski, Sebastian Riedel, and Luke Zettlemoyer. 2020. 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. find our card
  27. Urchade Zaratiana, Nadi Tomeh, Pierre Holat, and Thierry Charnois. 2023. Gliner: Generalist model for named entity recognition using bidirectional transformer. arXiv preprint arXiv:2311.08526. find our card
  28. Fangwei Zhu, Jifan Yu, Hailong Jin, Lei Hou, Juanzi Li, and Zhifang Sui. 2023. Learn to not link: Exploring nil prediction in entity linking. In Findings of the Association for Computational Linguistics: ACL 2023, pages 10846–10860. find
  29. Language Resource References Santini, Cristian and Barzaghi, Sebastian and Sernani, Paolo. 2025. ENEIDE: A High Quality Silver Standard Dataset for Named Entity Recognition and Linking in Historical Italian. Zenodo. PID https://doi.org/10.5281/zenodo.17407356. — [doi:10.5281/zenodo.17407356](https://doi.org/10.5281/zenodo.17407356) ↗

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/santini-2026-eneide-high-quality-silver-standard/