Conditional random fields and support vector machines for disorder named entity recognition in clinical texts

A comparative study between two machine learning methods, Conditional Random Fields and Support Vector Machines for clinical named entity recognition and their applicability to clinical domain is presented.

Abstract

We present a comparative study between two machine learning methods, Conditional Random Fields and Support Vector Machines for clinical named entity recognition. We explore their applicability to clinical domain. Evaluation against a set of gold standard named entities shows that CRFs outperform SVMs. The best F-score with CRFs is 0.86 and for the SVMs is 0.64 as compared to a baseline of 0.60.