Abstract The Acadmie Francaise institution is assigned and devoted to defending the French language and to making it a common heritage for all ¸ French speakers. The French Sign Language (LSF) has never had such a support. To face this situation, a reference tool has been created, supported by the French Ministry of Education and by the General Delegation to the French language and to languages of France. This tool is a collaborative website entirely bilingual French and LSF, and which proposes for each concept at least one definition and its associated descriptors in various knowledge fields. Before being spread on-line, the information given by users (text, picture, video, presentation) is examined by experts on form and content, and is validated or rejected by these experts with an explanation. Considering regional and sociological differences, several signs may be proposed and validated for one concept. Our project does not wish to choose the ”ideal sign”, but wants to submit to our identified users all the proposals and to list their comments (have they come across this sign and if so, in which context). A set of information is thus collected for each sign and can be related to users profiles. The website is therefore an exchange platform, but can also be used as a linguistics observatory. One of our main issues concerning the data organization was to manage to adjust users different viewpoints and different uses of the website. Indeed, our platforms goal is not to make a simple dictionary but to create a network of ontologies. Our other issue is now that we cannot use a rigid organization model, because our website must constantly evolve and include new concepts and new descriptions or functionalities, such as illustrations, homonyms, antonyms, etc. In this article we will first briefly describe our platforms goals, then present our specific data organization which allows for example several classifications to be used simultaneously. We will illustrate this approachs interest with a critic of Deweys classification, that we had at first implemented despite its limits (acceding to a precise concept is difficult, the organization is not intuitive, recent concepts or specific LSF concepts cannot be referenced, etc.). We will propose to replace it with classifications directly created by our users and corresponding to their expectations and needs. This way the tree diagram is built gradually and supervised by experts in each knowledge field. Each content thus goes with descriptors and classifiers allowing it to play different parts depending on the context. Therefore a content can at the same time be a concept, a classification theme or sub-theme, or an illustration – the context will mobilize the appropriate contents depending on their descriptors and classifiers. We will finally present our current work on integrating direct resources in LSF through descriptors defining a sign’s spatial position and its moves (hands, body and face), in order to highlight our platforms great ability to evolve. We will also show that this data organization allows an easy conversion to other countries sign languages.