What capacities enable linguistic interaction? While severalproposals have been advanced, little progress has been made incomparing and articulating them within an integrative frame-work. In this paper, we take initial steps towards a connec-tionist framework designed to systematically compare differ-ent cognitive models of social interactions. The frameworkwe propose couples two simple-recurrent network systems(Chang, 2002) to explore the computational underpinnings ofinteraction, and apply this modeling framework to predict thesemantic structure derived from transcripts of an experimen-tal joint decision task (Bahrami et al., 2010; Fusaroli et al.,2012). In an exploratory application of this framework, wefind (i) that the coupled network approach is capable of learn-ing from noisy naturalistic input but (ii) that integration of pro-duction and comprehension does not increase the network per-formance. We end by discussing the value of looking to tra-ditional parallel distributed processing as flexible models forexploring computational mechanisms of conversation.