A TEI-based Layout Annotation System for a Deeper Automatic Encoding of Documents Juliette Janès, Sarah Bénière, Lucence Ing, Simon Gabay, Thibault Clérice, Benoît Sagot Feb 1, 2026 PDF Hal Juliette Janès Engineer Récupération, encodage, maintenance et publication des données textuels en français et langues de France Lucence Ing Engineer - Project Manager Corpus, relations and project management Thibault Clérice Researcher Benoît Sagot Senior Researcher - Co-Leader Inria Senior Researcher en Natural Language Processing