Elamur Research⌕
☰
home / papers / 2026 / LombardoGraphia: Automatic Classification of Lombard Orthography Variants

LombardoGraphia: Automatic Classification of Lombard Orthography Variants

Summary

Lombard, which has roughly 3.8 million speakers across Northern Italy and Southern Switzerland, has no single agreed spelling standard. Writers use competing orthographies, so collecting data for NLP risks blending distinct varieties without noticing. The authors frame the task of identifying which orthography a text uses as a necessary step toward building separate corpora for each variety without imposing an artificial norm. They present LombardoGraphia, built from Lombard Wikipedia content that was cleaned and filtered to keep material usable for orthographic analysis. Each sample is labelled with one of nine spelling systems. These range from pan-Lombard polynomic systems to macro-dialectal and strictly local conventions. On this data they train and compare 24 classifiers, covering both classical and neural approaches with different feature types and encoding granularities. The strongest systems reach roughly 96% overall accuracy, but their per-class average is clearly lower. This gap shows that rare orthographies remain difficult because the data are imbalanced. The released resources give a first benchmark and practical tooling for variety-aware Lombard NLP.

Key points

  • The corpus contains 11,186 Lombard Wikipedia samples labelled with 9 orthographies, split into train, validation and test sets.
    • Pan-Lombard: NOL, SL.
    • Macro-dialectal: LOCC, LORUNIF.
    • Local: MILCLASS, BERGDUC, LSI, BREMOD, CRES.
  • The corpus includes metadata describing each orthographic system and its geographic distribution.
  • The authors evaluate 24 traditional and neural classification models.
  • The best models score 96.06% overall accuracy and 85.78% average class accuracy. Minority orthographies remain the main weakness.
  • The corpus, models and code are published as lmo_graphia on GitHub (edoardosignoroni/lmo_graphia). The authors suggest uses in corpus building, language identification and orthographic normalization.

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 10.63317/2vm9gj2ap9wq

@inproceedings{signoroni2026lombardographia,
  title = {{LombardoGraphia: Automatic Classification of Lombard Orthography Variants}},
  author = {Signoroni, Edoardo and Rychly, Pavel},
  booktitle = {Proceedings of the Fifteenth Language Resources and Evaluation Conference},
  year = {2026},
  doi = {10.63317/2vm9gj2ap9wq},
  url = {https://doi.org/10.63317/2vm9gj2ap9wq}
}

References

26 references, 1 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Noëmi Aepli, Antonios Anastasopoulos, Adrian-Gabriel Chifu, William Domingues, Fahim Faisal, Mihaela Gaman, Radu Tudor Ionescu, and Yves Scherrer. 2022. Findings of the VarDial evaluation campaign 2022. In Proceedings of the Ninth Workshop on NLP for Similar Languages, Varieties and Dialects, pages… find
  2. Gaetano Berruto. 1987. Lingua, dialetto, diglossia, dilalìa. In Johannes Holtus, Günter e Kramer, editor, Romania et Slavia adriatica. Festschrift für Zarko Muljačić, 1st edition, pages 57–81. Buske, Hamburg. find
  3. Giovanni Bonfadini. 2010. lombardi, dialetti. In Treccani Eds., editor, Enciclopedia dell’italiano. Treccani, online at https://www.treccani.it/enciclopedia/dialetti-lombardi_(Enciclopedia-dell%27Italiano)/\#Studi. ↗
  4. Lissander Brasca. 2011. Scriver Lombard, 1st adj. edition. Menaresta, Monza. find
  5. William Cavnar and John Trenkle. 1994. N-gram-based text categorization. Proceedings of the Third Annual Symposium on Document Analysis and Information Retrieval. find
  6. Andrea Ceolin. 2022. Neural networks for cross-domain language identification. phlyers @Vardial 2022. In Proceedings of the Ninth Workshop on NLP for Similar Languages, Varieties and Dialects, pages 99–108, Gyeongju, Republic of Korea. Association for Computational Linguistics. find
  7. Paolo Coluzzi, Lissander Brasca, and Simona Scuri. 2021. Revitalizing contested languages: The case of lombard. In Marco Tamburelli and Mauro Tosco, editors, Contested Languages: The hidden multilingualism of Europe, chapter 9, pages 163–182. John Benjamins, Amsterdam. find
  8. Paolo Coluzzi, Lissander Brasca, Marco Trizzino, and Simona Scuri. 2018. Language planning for italian regional languages: the case of lombard and sicilian. In Dieter Stern, Motoki Nomachi, and Bojan Belić, editors, Linguistic Regionalism in Eastern Europe and Beyond: Minority, Regional and Literary… find
  9. 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
  10. Tommi Jauhiainen, Marco Lui, Marcos Zampieri, Timothy Baldwin, and Krister Lindén. 2019. Automatic language identification in texts: a survey. J. Artif. Int. Res., 65(1):675–682. find our card
  11. Michele Loporcaro. 2009. Profilo Linguistico dei Dialetti Italiani, 1st edition. Manuali Laterza. Editori Laterza, Bari. find
  12. Giovan-Battista Melchiori. 1817. Vocabolario Bresciano-Italiano. Franzoni e socio. find
  13. Christopher Moseley and Alexandre Nicholas. 2010. Atlas of the World’s Languages in Danger, 3rd edition, volume 19 of Memory of Peoples. UN-ESCO, Paris. find
  14. NLLB Team, Marta R. Costa-jussà, James Cross, Onur Çelebi, Maha Elbayad, Kenneth Heafield, Kevin Heffernan, Elahe Kalbassi, Janice Lam, Daniel Licht, Jean Maillard, Anna Sun, Skyler Wang, Guillaume Wenzek, Al Youngblood, Bapi Akula, Loic Barrault, Gabriel Mejia Gonzalez, Prangthip Hansanti, John Hof… find
  15. Giulia Paganessi. 2017. Brazilian Bergamasch: an Italian language spoken in Botuverá (Santa Catarina, Brazil). Leiden University. find
  16. Alan Ramponi. 2024. Language varieties of Italy: Technology challenges and opportunities. Transactions of the Association for Computational Linguistics, 12:19–38. find
  17. Antonio Tiraboschi. 1873. Vocabolario dei Dialetti Bergamaschi Antichi e Moderni. Editrice Fratelli Bolis. find
  18. Gertjan van Noord. 1997. Textcat. find
  19. Marcos Zampieri, Preslav Nakov, and Yves Scher-errén. 2020. Natural language processing for similar languages, varieties, and dialects: A survey. Natural Language Engineering, 26(6):595-612. find
  20. Stefano Zappettini. 1859. Vocabolario Bergamasco-Italiano per ogni classe di persone e specialmente per la gioventù. Pagnoncelli, Bergamo. find
  21. Language Resource References Marta R. Costa-jussà, James Cross, Onur Çelebi, Maha Elbayad, Kenneth Heafield, Kevin Heffernan, Elahe Kalbassi, Janice Lam, Daniel Licht, Jean Maillard, Anna Sun, Skyler Wang, Guillaume Wenzek, Al Youngblood, Bapi Akula, Loic Barrault, Gabriel Mejia Gonzalez, Prangthip… find
  22. Scaling neural machine translation to 200 languages. Nature, 630(8018):841–846. find
  23. Alan Ramponi and Camilla Casula. 2023. DiatopIt: A corpus of social media posts for the study of diatopic language variation in Italy. In Tenth Workshop on NLP for Similar Languages, Varieties and Dialects (VarDial 2023), pages 187– 199, Dubrovnik, Croatia. Association for Computational Linguistics. find
  24. Edoardo Signoroni. 2022. Piötòst ché niènt, mèi piötòst-a manually revised lombard-italian parallel corpus. find
  25. RASLAN 2022 Recent Advances in Slavonic Natural Language Processing, page 105. find
  26. Jörg Tiedemann. 2009. News from opus - a collection of multilingual parallel corpora with tools and interfaces. In Recent Advances in Natural Language Processing, volume V, pages 237–248. find

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/signoroni-2026-lombardographia-automatic-classification-lombard-orthography/