Abstract
Language modeling approach plays an important role in many areas of natural language processing including speech recognition, machine translation, and information retrieval. In this paper, we propose a contribution for conceptual indexing of medical articles by using the MeSH (Medical Subject Headings) thesaurus, then we propose a tool for indexing medical articles called SIMA (System of Indexing Medical Articles) which uses a language model to extract the MeSH descriptors representing the document. To assess the relevance of a document to a MeSH descriptor, we estimate the probability that the MeSH descriptor would have been generated by language model of this document.