A Machine Translation Approach for Medical Terms

We describe the task of translating clinical term descriptions from Spanish to Brazilian Portuguese. We build a statistical machine translation system (SMT) using in-domain parallel corpora and available machine learning tools. The performance of this SMT was compared with general purpose machine translation systems available online. We used different techniques to validate the result of the different systems, using reference domain terminology and the occurrence of translated descriptions in a corpus of medical scientific literature and in domain specific web pages. We also use two sets of 1000 description terms that were revised and checked by a Portuguese speaker. The performance of the SMT we built had very good preliminary results.