This paper describes the ANNODIS ressource, a corpus of written French enriched with several markups, including a manual annotation of discourse structures. The resource is original in that it offers a diversified corpus representing several text types, and two annotations based on different approaches to discourse organisation. As well as a description of the ressource - annotated objects, composition of the corpus - the paper presents the theoretical underpinnings of the annotation models and the methodological choices underlying corpus preparation and annotation. It also sketches the potential contribution of such a resource for linguistics and NLP, and describes initial results of its exploitation.
