Mining a lexicon of technical terms and lay equivalents

Abstract

We present a corpus-driven method for building a lexicon of semantically equivalent pairs of technical and lay medical terms. Using a parallel corpus of abstracts of clinical studies and corresponding news stories written for a lay audience, we identify terms which are good semantic equivalents of technical terms for a lay audience. Our method relies on measures of association. Results show that, despite the small size of our corpus, a promising number of pairs are identified.