Elamur Research⌕
☰
home / papers / 2026 / EDDA-Coordinata: An Annotated Dataset of Historical Geographic Coordinates

EDDA-Coordinata: An Annotated Dataset of Historical Geographic Coordinates

Summary

Eighteenth- and nineteenth-century reference works give geographic coordinates in many non-standard ways. Precision varies, latitude or longitude may be missing, and longitudes are counted from old prime meridians. This makes automatic extraction difficult. The authors built EDDA-Coordinata, a gold standard drawn from Diderot and d'Alembert's Encyclopédie. They double-annotated every geographic article in both the ARTFL and ENCCRE digitizations, then merged the two annotation sets. Each coordinate is stored as a string inside nested lists. This structure covers single points, bounding boxes, river polylines, subentries and conflicting sources, and the values are converted to modern Greenwich-based decimal degrees. On this data they trained a two-stage pipeline: a classifier first flags coordinate-bearing articles, then a sequence-to-sequence model extracts and normalizes the values. They compared encoder–decoder and decoder-only architectures. The approach performs well within the Encyclopédie and also transfers reasonably to another French dictionary and to an English encyclopedia. This makes it practical to map and compare numerical versus descriptive place information at scale in historical corpora.

Key points

  • Of roughly 74,000 Encyclopédie articles, 15,278 are geographic. Of these, 4,798 contain explicit coordinates and 10,480 locate places only in prose.
  • Inter-annotator agreement was 0.98 for points but only 0.52 for surfaces (bounding boxes).
  • Longitudes, mostly given 0–360° east of El Hierro (set at 20° west of Paris), are shifted by about 17.66° to the Greenwich standard. Annotations use the prefixes pchain, subart and multsrc and are validated with geopy.Point.
  • Exact match (EM) scores:
    • 86% in cross-validation on the Encyclopédie.
    • 61% on the out-of-domain French Dictionnaire de Trévoux.
    • 77% on the English 7th edition of the Encyclopædia Britannica.
  • The dataset, models, code and a demo are released on Hugging Face (GEODE) and GitHub (GEODE-project/edda-coordinata).

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

Cite

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.63317/5guc63fgjocp

@inproceedings{moncla2026edda,
  title = {{EDDA-Coordinata: An Annotated Dataset of Historical Geographic Coordinates}},
  author = {Moncla, Ludovic and Nugues, Pierre and Joliveau, Thierry and McDonough, Katherine},
  booktitle = {Proceedings of the Fifteenth Language Resources and Evaluation Conference},
  year = {2026},
  doi = {10.63317/5guc63fgjocp},
  url = {https://doi.org/10.63317/5guc63fgjocp}
}

References

41 references, 4 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Elise Acheson and Ross S. Purves. 2021. Extracting and modeling geographic information from scientific articles. PLOS ONE, 16(1):e0244918. find
  2. G. Blanchy, L. Albrecht, J. Koestel, and S. Garré. 2023. Potential of natural language processing for metadata extraction from environmental scientific publications. SOIL, 9(1):155–168. find
  3. Alice Brenon, Ludovic Moncla, and Katherine Mc-Donough. 2022. Classifying encyclopedia articles: Comparing machine and deep learning methods and exploring their predictions. Data & Knowledge Engineering, 142:102098. find
  4. Ronan Collobert, Jason Weston, Léon Bottou, Michael Karlen, Koray Kavukcuoglu, and Pavel Kuksa. 2011. Natural language processing (almost) from scratch. Journal of Machine Learning Research, 12(76):2493–2537. find our card
  5. TEI Consortium. 2025. Guidelines for electronic text encoding and interchange. find
  6. Jean Le Rond d’Alembert and Denis Diderot. 1751-1772. Encyclopédie, ou Dictionnaire raisonné des Sciences, des Arts et des Métiers, etc. Chez Briasson, Paris. find
  7. 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,… find
  8. Dictionnaire universel françois et latin. 1743. Dictionnaire universel françois et latin. Étienne Ganeau, Trévoux. find
  9. Matthew H. Edney. 1999. Geography and Enlightenment, chapter 6. University of Chicago Press, Chicago. find
  10. Maud Ehrmann, Ahmed Hamdi, Elvys Linhares Pontes, Matteo Romanello, and Antoine Doucet. 2023. Named entity recognition and classification in historical documents: A survey. ACM Computing Surveys, 56(2):1–47. find
  11. Encyclopædia Britannica. 1842. The encyclopædia Britannica, or, Dictionary of arts, sciences, and general literature ... with preliminary dissertations on the history of the sciences, and other extensive improvements and additions ; including the late supplement, a general index, and numerous engrav… find
  12. Alexandre Guilbaud, Irène Passeron, Marie Leca-Tsiomis, Olivier Ferret, Vincent Barrellon, and Yoichi Sumi. 2013. « entrer dans la forteresse»: pour une édition numérique collaborative et critique de l’Encyclopédie (projet ENCCRE). Recherches sur Diderot et sur l’Encyclopédie, (48):225–261. find
  13. Thora Hagen, Erik Ketzan, Fotis Jannidis, and Andreas Witt. 2020. Twenty-two historical encyclopedias encoded in TEI: a new resource for the digital humanities. In Proceedings of the 4th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literat… find
  14. Sepp Hochreiter and Jürgen Schmidhuber. 1997. Long short-term memory. Neural computation, 9(8):1735–1780. find
  15. Russell Horton, Robert Morrissey, Mark Olsen, Glenn Roe, and Robert Voyer. 2009. Mining eighteenth century ontologies: machine learning and knowledge classification in the encyclopédie. In The Alliance of Digital Humanities Organizations, volume 3. find
  16. Thierry Joliveau, Ludovic Moncla, Antoine Taroni, Denis Vigier, and Katherine McDonough. 2024. A digital exploration of geographic knowledge in Diderot and d’Alembert’s encyclopédie. In 30th International Conference on the History of Cartography (ICHC). find
  17. Christopher B. Jones and Ross S. Purves. 2008. Geographical information retrieval. International Journal of Geographical Information Science, 22(3):219–228. find
  18. Taku Kudoh and Yuji Matsumoto. 2000. Use of support vector learning for chunk identification. In Proceedings of CoNLL-2000 and LLL-2000, pages 142–144, Lisbon. find
  19. Lucie Lagarde. 1979. Historique du problème du Méridien origine en France. Revue d’histoire des sciences, 32(4):289–304. find
  20. Ziran Liu et al. 2023. An empirical study of pre-trained language models in simple information extraction tasks. arXiv preprint arXiv:2305.14953. — [arXiv:2305.14953](https://arxiv.org/abs/2305.14953) find
  21. Katherine McDonough, Ludovic Moncla, and Matje van de Camp. 2019. Named entity recognition goes to old regime France: geographic text analysis for early modern French corpora. International Journal of Geographical Information Science, 33(12):2498–2522. find
  22. Ludovic Moncla, Denis Vigier, and Katherine Mcdonough. 2024. Geoedda: A gold standard dataset for geo-semantic annotation of Diderot & d’Alembert’s Encyclopédie. In Second International Workshop on Geographic Information Extraction from Texts (GeoExT) at the European Conference on Information Retrie… find
  23. Robert Morrissey, John Iverson, and Mark Olsen. 1998. L’Encyclopédie de Diderot sur Internet. Recherches sur Diderot et sur L’Encyclopédie, (25). find
  24. Paolo Nesi, Gianni Pantaleo, and Marco Tenti. 2014. Ge(o)lo(cator): Geographic information extraction from unstructured text data and web documents. In 2014 9th International Workshop on Semantic and Social Media Adaptation and Personalization, pages 60–65. find
  25. Pierre Nugues. 2024. Linking named entities in Diderot’s Encyclopédie to wikidata. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 10610–10615, Torino, Italy. ELRA and ICCL. find
  26. Terry Quinn. 2012. From Artefacts to Atoms: The BIPM and the Search for Ultimate Measurement Standards. Oxford University Press, Oxford. find
  27. Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, and Peter J Liu. 2020. Exploring the limits of transfer learning with a unified text-to-text transformer. Journal of Machine Learning Research, 21(140):1–67. find
  28. Glenn Roe, Clovis Gladstone, and Robert Morrissey. 2016. Discourses and disciplines in the enlightenment: Topic modeling the french encyclopédie. Frontiers in Digital Humanities, 2:8. find
  29. Charles Sutton and Andrew McCallum. 2011. An introduction to conditional random fields. Foundations and Trends in Machine Learning, 4(4):267– 373. find
  30. Erik F. Tjong Kim Sang. 2002. Introduction to the CoNLL-2002 shared task: Language-independent named entity recognition. In COLING-02: The 6th Conference on Natural Language Learning 2002 (CoNLL-2002). find our card
  31. Erik F. Tjong Kim Sang and Sabine Buchholz. 2000. Introduction to the CoNLL-2000 shared task chunking. In Fourth Conference on Computational Natural Language Learning and the Second Learning Language in Logic Workshop. find our card
  32. Erik F. Tjong Kim Sang and Fien De Meulder. 2003. Introduction to the CoNLL-2003 shared task: Language-independent named entity recognition. In Proceedings of the Seventh Conference on Natural Language Learning at HLT-NAACL 2003, pages 142–147. find
  33. Erik F. Tjong Kim Sang and Hervé Déjean. 2001. Introduction to the CoNLL-2001 shared task: clause identification. In Proceedings of the ACL 2001 Workshop on Computational Natural Language Learning (ConLL). find
  34. Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Łukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. In Advances in Neural Information Processing Systems, volume 30. Curran Associates, Inc. find
  35. Denis Vigier, Ludovic Moncla, Isabelle Lefort, Thierry Joliveau, and Katherine McDonough. 2022. Les articles de géographie dans le Dictionnaire Universel de Trévoux et l’Encyclopédie de Diderot et d’Alembert. Langue française, 214(2):59–80. find
  36. Shuhe Wang, Xiaofei Sun, Xiaoya Li, Renjie Ouyang, Fei Wu, Tianwei Zhang, Jiwei Li, and Guoyin Wang. 2023. Gpt-ner: Named entity recognition via large language models. arXiv preprint arXiv:2304.10428. find our card
  37. Linting Xue, Noah Constant, Adam Roberts, Mihir Kale, Rami Al-Rfou, Aditya Siddhant, Aditya Barua, and Colin Raffel. 2021. mT5: A massively multilingual pre-trained text-to-text transformer. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Ling… find
  38. Language Resource References ARTFL. 2022. Encyclopédie, ou dictionnaire raisonné des sciences, des arts et des métiers, etc. Robert Morrissey and Glenn Roe (eds), University of Chicago: ARTFL Encyclopédie Project. find
  39. ENCCRE. 2017. Édition Numérique Collaborative et Critique de l’Encyclopédie (ENCCRE). Académie des sciences, 1.0. find
  40. Nineteenth Century Knowledge Project. 2025. Encyclopedia Britannica, Seventh Edition: A Machine-Readable Text Transcription. Peter M. Logan (ed.), Temple University. find
  41. Projet TRÉVOUX. 2026. Edition numérique du Dictionnaire Universel François & Latin, vulgairement appellé Dictionnaire de Trévoux. Ludovic Moncla and Denis Vigier (eds), INSA Lyon / LIRIS CNRS and Université Lumière Lyon 2 / ICAR CNRS. find

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/moncla-2026-edda-coordinata-annotated-dataset-historical/