Automatic acquisition of morphological knowledge for medical language processing

Medical words exhibit a rich and productive morphology. Morphological knowledge is therefore very important for any medical language processing application. We propose a simple and powerful method to acquire automatically such knowledge. It takes advantage of commonly available lists of synonym terms to bootstrap the acquisition process. We experimented it on the SNOMED International Microglossary fur pathology in its French version. The families of morphologically related words that we obtained were useful for query expansion in a coding assistant. Since the method does not rely on a priori linguistic knowledge, it is applicable to other languages such as English.