NegEx is a popular rule-based system used to identify negated concepts in clinical notes. This system has been reported to perform very well by numerous studies in the past. In this paper, we demonstrate the use of kernel methods to extend the performance of NegEx. A kernel leveraging the rules of NegEx and its output as features, performs as well as the rule-based system. An improvement in performance is achieved if this kernel is coupled with a bag of words kernel. Our experiments show that kernel methods outperform the rule-based system, when evaluated within and across two different open datasets. We also present the results of a semi-supervised approach to the problem, which improves performance on the data.