Automatic Normalisation of Middle French and its Impact on Productivity

Conférence Chapitre d'actes Automatic Normalisation of Middle French and its Impact on Productivity eng 2024-05 author Rubino Raphaël 416655 Département de traitement informatique multilingue (TINFM) author Coram-Mekkey Sandra 46026 author Gerlach Johanna 0000-0002-3371-4021 645950 Département de traitement informatique multilingue (TINFM) author Mutal Jonathan David 0000-0001-7729-8456 896440 Département de traitement informatique multilingue (TINFM) author Bouillon Pierrette 0000-0002-8854-6360 26962 Département de traitement informatique multilingue (TINFM) 176-189 978-2-493814-46-3 https://aclanthology.org/2024.lt4hala-1.20/ This paper presents a study on automatic normalisation of 16th century documents written in Middle French. These documents present a large variety of wordforms which require spelling normalisation to facilitate downstream linguistic and historical studies. We frame the normalisation process as a machine translation task starting with a strong baseline leveraging a pre-trained encoder–decoder model. We propose to improve this baseline by combining synthetic data generation methods and producing artificial training data, thus tackling the lack of parallel corpora relevant to our task. The evaluation of our approach is twofold, in addition to automatic metrics relying on gold references, we evaluate our models through post-editing of their outputs. This evaluation method directly measures the productivity gain brought by our models to experts conducting the normalisation task manually. Results show a 20+ token per minute increase in productivity when using automatic normalisation compared to normalising text from scratch. The manually post-edited dataset resulting from our study is the first parallel corpus of normalised 16th century Middle French to be publicly released, along with the synthetic data and the automatic normalisation models used and trained in the presented work. Intralingual diachronic translation Middle French Archive Normalisation Productivity Dewey 410.2 ELRA Torino, Italia Swiss National Science Foundation Une édition sémantique et multilingue en ligne des registres du Conseil de Genève (1545-1550) 215733 CH Projects 112 Département de traitement informatique multilingue 92 false 696 TIM/ISSCO Proceedings of the Third Workshop on Language Technologies for Historical and Ancient Languages (LT4HALA) @ LREC-COLING-2024 Rachele Sprugnoli and Marco Passarotti 25 May, 2024 Torino 1dae26f1-1798-4cd5-8297-9c37086484a0 Proceedings chapter (Published version) Public 2024.lt4hala-1.20.pdf 501716 application/pdf CC BY-NC-4.0 4d96cc215667177c64ec0f9752665527b5041252af08909f98f7e5fadf65ae25 ce99d13a-7dc3-4b32-a339-5d437179c436 Summary Public lt4hala24_presentation.pdf 1627469 application/pdf CC BY-NC-4.0 Slides 7e39e42d4af1e00e605ec0cec4c4383cff358c94e271183d74401279f5e43779 openAccess Faculté de traduction et d'interprétation / Département de traitement informatique multilingue

Title	Published in	Access level	OA Policy	Year	Views	Downloads

Automatic Normalisation of Middle French and its Impact on Productivity	Proceedings of the Third Workshop on Language Technologies for Historical and Ancient Languages (LT4HALA) @ LREC-COLING-2024			2024	144	112

Archive ouverte UNIGE

Coram-Mekkey, Sandra