Proceedings of the Annual Meeting of the Cognitive Science Society

We propose a computational model of verb learning implemented as a probabilistic compositional semantic parser, thatjointly learns individual verb meanings and overarching associations between syntactic verb frames and compositionalsemantic predicates from distant supervision on grounded natural language data. In tandem, we present a new corpus fortraining and evaluating grounded language learning models, containing natural language descriptions of scenes generatedin a rich environment that simulates realistic interactions between animate agents and physical objects. We demonstratehow the model can acquire interpretable correspondences between syntactic frames by incrementally parsing individ-ual sentences, evaluating candidate verb meanings on grounded scenes, and investigate how the models acquired framesemantics priors generalize to support efficient inferences about the meanings of novel verbs on a few shot learning task.