It is well-established that toddlers can correctly select a novel referent from an ambiguous array in response to a novel label, or fast-map (Carey, 1978). There is a growing consensus this ability depends at least in part on a mutual exclusivity-type process; that is, if all-but-one objects in an array have a label (“known objects”), the novel label must refer to the novel object. However, the precise mechanism underlying this phenomenon is debated. Horst, Scott & Pollard (2010) shed light on this issue by investigating the effect of contetxt on word learning. The authors familiarised two-year-old children with novel label-object mappings by asking them to select the single novel object from among the known objects in arrays of three, four or five toys. At test, when presented with arrays of just-seen novel objects, only children who had encountered the novel label/object mappings in three-object arrays reliably recalled these mappings; children who saw four- or five-object arrays did not recall mappings at levels greater than expected by chance. The authors argued that attention to competitor objects is fundamental to the “mutual exclusivity” process and, by extension, word learning. Here, we use a computational model to explore whether this behaviour can emerge from simple associative processes, or whether higher-level reasoning is required. We present a developmental robotic replication of Horst and colleagues’ original study using a variant of the connectionist Epigenetic Robotic Architecture (Morse, de Greeff, Belpeame, & Cangelosi, 2010) implemented in the iCub humanoid robot (Metta et al., 2010). The replication demonstrates that the apparently complex reasoning demonstrated by the children in the target empirical study emerege from low-level inhibitory processes in the computational model ; more generally the current study indicates that word learning may depend on relatively simple bottom-up perceptual processing rather than complex, top-down reasoning.