Finding Medical Term Variations using Parallel Corpora and Distributional Similarity
Lonneke van der Plas, Jörg Tiedemann · 2010
We describe a method for the identification of medical term variations using parallel corpora and measures of distributional similarity. Our approach is based on automatic word alignment and standard phrase extraction techniques commonly used in statistical machine translation. Combined with pattern-based filters we obtain encouraging results compared to related approaches using similar datadriven techniques. 1