Summary
Gaël Lejeune is an Associate Professor in Computer Science at Sorbonne Université with over a decade of experience specializing in natural language processing and text mining, particularly for press, microblogs and PDF documents. His work spans classification tasks (dating, emotion detection, multilingual monitoring, information extraction) and content extraction (OCR, scraping, automated table of contents), with a strong track record from PhD research on multilingual epidemic surveillance through to postdoctoral projects in dialogue modeling and biomedical text mining. He combines academic teaching and research with practical system-building experience, having implemented multilingual surveillance architectures and experimental platforms in industry collaborations. Fluent in both linguistic and technical perspectives—rooted in degrees in computer science, translation/cognitive sciences and language studies—he brings a rare multidisciplinary approach to NLP problems. Notably, he applies research methods to messy real-world documents (native or scanned PDFs), bridging state-of-the-art algorithms with robust data acquisition and preprocessing.
10 years of coding experience
Doctor of Philosophy (PhD), Informatique, Doctor of Philosophy (PhD), Informatique at Université de Caen Normandie
English, Spanish, Russian