The feasibility of automatic restructuring of nonnumerical programs for parallel processing is studied through experiments of Parafrase, an automatic restructurer. Parallel processing speedup results due to automatic restructuring for several basic nonnumerical problems are presented. Based on the speedup results and the analysis of the loop types encountered, the difficulty and the effectiveness of automatic restructuring are discussed. The experiments suggest that automatic restructuring can be a useful tool for exploiting parallelism in the sequential form of nonnumerical programs.