Apprentissage artificiel de règles d’indexation pour MEDLINE

Indexing is a crucial step in any information retrieval system. In MEDLINE, a widely used database of the biomedical literature, the indexing process involves the selection of Medical Subject Headings in order to describe the subject matter of articles. The need for automatic tools to assist human indexers in this task is growing with the increasing amount of publications to be referenced in MEDLINE. In this paper, we describe the use and the customiza- tion of Inductive Logic Programming (ILP) to infer indexing rules that may be used to produce automatic indexing recommendations for MEDLINE indexers. Our results show that this origi- nal ILP-based approach overperforms manual rules when they exist. We expect the sets of ILP rules obtained in this experiment to be integrated in the system producing automatic indexing recommendations for MEDLINE.