New wine in old wineskins: a morphology-based approach to translate medical terminology

In this work we introduce the first steps toward the development of a machine translation system for medical terminology. We explore the possibility of basing a machine translation task in the medical domain on morphology. Starting from neoclassical formative elements, or confixes, we started building MedIta, a cross-language ontology of medical morphemes, aiming to offer a standardized medical consistent resource that includes distributional and semantic information of medical morphemes. Using this information, we have built an ontology-driven Italian-English machine translation prototype, based on a set of Finite State Transducers, and we have carried out an experiment on Orphanet medical corpus to evaluate the feasibility of this approach.