Cover not available

Article published In: Researching Occitan in the 21st Century: Un dialòg interdisciplinari
Edited by Marc Olivier and Anna Paradis
[Revue Romane 60:1] 2025
► pp. 30–42

Get fulltext from our e-platform
JBE logo with link
PDF logo with download linkDownload PDF
EPUB logo with download linkDownload EPUB
authorization required

Framework to build and lemmatise an Occitan historical corpus

 | Sorbonne Université STIH
Published online: 15 December 2025
DOI logo with link
https://doi.org/10.1075/rro.25009.cou
Abstract
This paper presents a framework for building lemmatised Occitan corpora, focusing on early modern texts. Due to strong dialectal and diachronic variation, lemmatisation is essential for enabling cross-text and cross-period comparison. We adopt a semi-automatic approach based on the Pie neural model, combining tokenisation, super-lemma selection, and POS tagging aligned with Universal Dependencies. Initial experiments on 17th–18th century texts show promising results, particularly for frequent and grammatical words, while highlighting challenges with unknown lemmas. Despite its exploratory scope, the study demonstrates the feasibility of cost-effective corpus construction and lays the groundwork for a larger, more representative language model of Occitan.
Article outline
  • 1.Occitan corpus linguistics and lemmatisation
  • 2.General guidelines
    • 2.1Tokenisation
    • 2.2Lemmas
    • 2.3POS tagging
  • 3.From fac-simile to annotated data
    • 3.1Data
      • 3.1.2Methodology and results
      • 3.1.3Exemples of research question
  • 4.Conclusion
  • Note
  • References
References (24)
References
Alibèrt, L. ([1976] 2000). Gramatica occitan segon los parlars lengadocians. Tolosa, Barcelona, IEO, IEC.Google Scholar logo with link to Google Scholar
Francioni, B., Romanova, N., Ziane, R. (2025). First steps towards building a treebank of Old Gascon. Talk at Data in Historical Linguistics seminar, London, King’s College.
Bras, M., Vergez-Couret, M., & Sibille, J. (2024). Corpus et bases de données. Manuel de linguistique occitane, Berlin, DeGruyter, 523–542. Google Scholar logo with link to Google Scholar
Camps, J. B., Couffignal, G. (2020). La production de corpus d’occitan médiéval et prémoderne : problèmes et perspectives de travail, in Jean-François Courouau et David Fabié (dir.), Fidélités et dissidences / Fidelitats et dissidéncias, actes du XIIe Congrès de l’Association Internationale d’Études Occitanes. Toulouse, SFAIEO, vol. 21, 639–652.Google Scholar logo with link to Google Scholar
Chambon, J. P. (2017). Brèves remarques sur le Tresor dóu Felibrige de Frédéric Mistral. In Méthodes de recherche en linguistique et en philologie romanes. Strasbourg, EliPhi, 259–274.Google Scholar logo with link to Google Scholar
Couffignal, G. (forth. a). Philologie numérique et données bruitées : un exemple de recherche sur l’occitan prémoderne, in Robert Hesselbach et Tanja Prohl (dir.) Approches numériques des corpus historiques des langues de France.
(forth. b). Le noël occitan imprimé à Toulouse au XVIIe siècle : une approche textométrique. In Littératures classiques, special issue directed by J.F. Courouau.
Courouau, J. F. (2024). Contact avec le français et registres de l’occitan moderne (XVIe-XVIIIe siècle), Lengas, 941, [URL]
Field, T. (2013). The Linguistic Corpus of Old Gascon. Database for linguistic research on Southwestern France, [URL]
Lafon, P. (1980). Sur la variabilité de la fréquence des formes dans un corpus. Mots, 11, 127–165. Google Scholar logo with link to Google Scholar
Léonard, J.-L., Brun-Trigaud, G., Picard, F. (2024). Atlas linguistiques et perspectives dialectométriques. In Manuel de linguistique occitane. Berlin, DeGruyter, 473–520. Google Scholar logo with link to Google Scholar
Levy, E. (1924). Provenzalisches Supplement-Wörterbuch. Leipzig, OR Reisland.Google Scholar logo with link to Google Scholar
Manjavacas, E., Kádár, Á., and Kestemont, M. (2019). Improving Lemmatization of Non-Standard Languages with Joint Learning. 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). Minneapolis, Minnesota. Association for Computational Linguistics, 1493–1503. Google Scholar logo with link to Google Scholar
Miletić, A. (2023). Outiller l’occitan: nouvelles ressources et lemmatisation. In 18e Conférence en Recherche d’Information et Applications--16e Rencontres Jeunes Chercheurs en RI--30e Conférence sur le Traitement Automatique des Langues Naturelles--25e Rencontre des Étudiants Chercheurs en Informatique pour le Traitement Automatique des Langues. ATALA, 217–231.Google Scholar logo with link to Google Scholar
Miletić, A., and Siewert, J. (2023). Lemmatization Experiments on Two Low-Resourced Languages: Low Saxon and Occitan. In Tenth Workshop on NLP for Similar Languages, Varieties and Dialects (VarDial 2023), Dubrovnik, Association for Computational Linguistics, 163–173.Google Scholar logo with link to Google Scholar
Miletić, A., Bras, M., Vergez-Couret, M., Esher, L., Poujade, C., & Sibille, J. (2020). A four-dialect treebank for Occitan: Building process and parsing experiments. In Proceedings of the 7th Workshop on NLP for Similar Languages, Varieties and Dialects, 140–149.Google Scholar logo with link to Google Scholar
Mistral, F. (1878). Lou Tresor dòu Felibrige ou dictionnaire provençal-français. Avignon, Veuve Remondet-Aubin.Google Scholar logo with link to Google Scholar
Rainsford, Thomas M. 2025. Old Gallo-Romance Corpus, version 1.0. Stuttgart: Institut für Linguistik/Romanistik. 〈[URL]〉
Raynouard, F. J. M. (1840). Lexique roman, ou, dictionnaire de la langue des troubadours. Paris, Silvestre.Google Scholar logo with link to Google Scholar
Ricketts, P. T. (2001). Concordance de l’occitan médiéval. Turnhout, Brepols.Google Scholar logo with link to Google Scholar
Sauzet, P. (2014). Idiomacitat e diglossia. In Amb un fil d’amistat. Mélanges offerts à Philippe Gardy. Toulouse, SFAIEO, 855–866.Google Scholar logo with link to Google Scholar
Scrivner, O., Kübler, S., Vance, B., & Beuerlein, E. (2013). Le Roman de Flamenca: An annotated corpus of old Occitan. In Proceedings of the Third Workshop on Annotation of Corpora for Research in Humanities, 85–96.Google Scholar logo with link to Google Scholar
Stempel, W. D., Selig, M., Kraus, C., Peter, R., & Tausend, M. (1996). Dictionnaire de l’occitan médiéval (DOM en ligne), [URL]
Thalamus team (2014). Édition critique numérique du manuscrit AA9 des Archives municipales de Montpellier dit Le Petit Thalamus. Université Paul Valéry Montpellier-III, [URL]
Mobile Menu Logo with link to supplementary files background Layer 1 prag Twitter_Logo_Blue