We report results of experiments which build and refine models of rhetorical-semantic relations such as Cause and Contrast. We adopt the approach of Marcu and Echihabi (2002), using a small set of patterns to build relation models, and extend their work by refining the training and classification process using parameter optimization, topic segmentation and syntactic parsing. Using human-annotated and automatically-extracted test sets, we find that each of these techniques results in improved relation classification accuracy.