In this paper, we apply named entity recognition techniques to a corpus of literary texts, i.e. French novels from the 18 th , 19 th and 20 th century. We obtain results that are usable but could be improved by using advanced annotation techniques. We discuss the use of active learning in this context, as well as the different applications that could be derived from this kind of annotation. In particular, we show that the automatic annotation of large literary corpora makes it possible to check whether traditional classifications exhibit specific structural patterns that could be identified automatically.