This paper presents a discriminative reranking model for the discourse segmentation task, the first step in a discourse parsing system. Our model exploits subtree features to rerank N-best outputs of a base segmenter, which uses syntactic and lexical features in a CRF framework. Experimental results on the RST Discourse Treebank corpus show that our model outperforms existing discourse segmenters in both settings that use gold standard Penn Treebank parse trees and Stanford parse trees. 1