Abstract This chapter hypothesizes that integrating multiple probabilistic cues (phonological, prosodic, and distributional) by perceptually attuned general-purpose learning mechanisms, may hold promise for explaining how children solve the bootstrapping problem. Multiple cues can provide reliable evidence about linguistic structure that is unavailable from any single source of information. The chapter first reviews empirical evidence suggesting that infants may use a combination of phonological, prosodic, and distributional cues to bootstrap into syntax. It then reports a series of simulations demonstrating the computational efficacy of multiple-cue integration within a connectionist framework.