The wordnet model is the most widespread model for representing lexical semantics based on an a priori inventory of meanings. Following the Princeton WordNet of English, wordnet-type resources have been developed for dozens of languages, including French, most often using automatic or semi-automatic techniques. In this article, we first review the characteristics and limitations of the wordnet model. We then present a panorama of wordnet development methods. We finally illustrate our own work in this area on the development of WOLF, the free French wordnet.