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.

One hallmark of human language is its combinatoriality---reusing a relatively small inventory of building blocks to create a far larger inventory of increasingly complex structures. In this paper, we explore the idea that combinatoriality in language reflects a human inductive bias toward representational efficiency in symbol systems. We develop a computational framework for discovering structure in a writing system. Built on top of state-of-the-art library learning and program synthesis techniques, our computational framework discovers known linguistic structures in the Chinese writing system and reveals how the system evolves towards simplification under pressures for representational efficiency. We demonstrate how a library learning approach, utilizing learned abstractions and compression, may help reveal the fundamental computational principles that underlie the creation of combinatorial structures in human cognition, and offer broader insights into the evolution of efficient communication systems.