The CLARA-MeD project applies automatic natural language processing methods to enhance the accessibility of health information.

One of the approaches is term simplification; i.e. substituting a difficult-to-read word (e.g. amigdalectomía) with an easier or more explicative paraphrase (e.g. operación de anginas).

The CLARA-MeD repository includes the following work:

• A parallel corpus of technical-patient aligned sentences, extracted from the CLARA-MeD comparable corpus of technical and laymen documents.
• Models used in experiments to compare simplification approaches based on state-of-the-art neural-network algorithms.