Paper: ULisboa: Identification and Classification of Medical Concepts

ACL ID S14-2127
Title ULisboa: Identification and Classification of Medical Concepts
Venue Joint Conference on Lexical and Computational Semantics
Year 2014

This paper describes our participation on Task 7 of SemEval 2014, which fo- cused on the recognition and disambigua- tion of medical concepts. We used an adapted version of the Stanford NER sys- tem to train CRF models to recognize tex- tual spans denoting diseases and disor- ders, within clinical notes. We consid- ered an encoding that accounts with non- continuous entities, together with a rich set of features (i) based on domain spe- cific lexicons like SNOMED CT, or (ii) leveraging Brown clusters inferred from a large collection of clinical texts. Together with this recognition mechanism, we used a heuristic similarity search method, to assign an unambiguous identifier to each concept recognized in the text. Our best run on Task A (i.e., in the recog- nition of medical concepts in the ...