TAKELAB: Medical Information Extraction and Linking with MINERAL

摘要

Medical texts are filled with mentions of diseases, disorders, and other clinical conditions, with many different surface forms relating to the same condition. We describe MINERAL, a system for extraction and normalization of disease mentions in clinical text, with which we participated in the Task 14 of SemEval 2015 evaluation campaign. MINERAL relies on a conditional random fields-based model with a rich set of features for mention detection, and a semantic textual similarity measure for entity linking. MINERAL reaches joint extraction and linking performance of 75.9% relaxed F_1-score (strict score of 72.7%) and ranks fourth among 16 participating teams.