This study was designed to investigate the effects of script-based and nonscript-based treatment on the language comprehension of 4 preschool children with mental retardation. An alternating treatments design (ATD) in combination with a multiple baseline design was used to evaluate treatment effects. Treatments were comprised of three script routines and three nonscript activities. Two semantic constructions were selected for training and counterbalanced across subjects and treatments. Daily probes were administered to assess the effects of the treatments. The script-based treatment was more effective than the nonscript treatment in facilitating comprehension of the targeted semantic constructions in 3 of the 4 subjects.