In this article, we present a method for extracting automati cally from texts semantic relations in the medical domain using linguistic patterns. These patterns refer to three levels of informati on about words: inflected form, lemma and part-of-speech. Th e method we present consists first in identifying the entities that are p art of the relations to extract, that is to say diseases, exam s,
... [Show full abstract] treatments, drugs or symptoms. Thereafter, sentences that contain couples of entities are extracted and the presence of a semantic relati on is validated by applying linguistic patterns. These patterns were previ ously learnt automatically from a manually annotated corpus by relying on an algorithm based on the edit distance. We first report the resu lts of an evaluation of our medical entity tagger for the five t ypes of entities we have mentioned above and then, more globally, the results of an evaluation of our extraction method for four relations between these entities. Both evaluations were done for French.
