This paper explores computational models of multi-party discourse, using transcripts from U.S. Supreme Court oral arguments. The turn-taking behavior of participants is treated as a supervised sequence labeling problem and modeled using first- and secondorder Conditional Random Fields. We specifically explore the hypothesis that discourse markers and personal references provide important features in such models. Results from a sequence prediction experiment demonstrate that incorporating these two types of features yields significant improvements in performance. This work is couched in the broader context of developing tools to support legal scholarship, although we see other NLP applications as well.