
Reading Byzantine seal monograms
Detection + classification pipeline for Greek characters: mAP@50 0.778, 96.7% accuracy. DH2026 paper.
From linguistic fieldwork to language engineering: from sociolinguistic surveys during my bachelor's to deep learning models in my master's, the same interest in how language is read, by humans and by machines.

Detection + classification pipeline for Greek characters: mAP@50 0.778, 96.7% accuracy. DH2026 paper.

Corpus audit (80% duplicates), weighted loss, tuned threshold: F1 0.83, precision 0.79, recall 0.88.

Educational web app: 7 tracks, 143 questions, an interactive lab, Python in the browser.

Fusing seismic data and audio signals: concatenation, stacking, voting.

OWL 2 + 6 SWRL rules: the reasoner dates, classifies and locates the objects.

Search by meaning: sentence embeddings and exact cosine similarity.
Bachelor's in Language Sciences, Université de Franche-Comté (now Université Marie & Louis Pasteur), Besançon.