The idea that optimization plays a key role in linguistic cognition is supported by an increasingly large body of research. Building on this research, we describe a new approach to parsing distributed representations via optimization over a set of soft constraints on the wellformedness of parse trees. This work extends previous research involving the use of constraintbased or “harmonic”’ grammars by suggesting how parsing can be accomplished using fully distributed representations that preserve their dimensionality with arbitrary increases in structural complexity. We demonstrate that this method can be used to correctly evaluate the wellformedness of linguistic structures generated by a simple context-free grammar, and discuss a number of extensions concerning the neural implementation of the method and its application to complex parsing tasks.

Cognitive models have long been used to study linguistic phe-nomena spanning the domains of phonology, syntax, and se-mantics. Of these domains, semantics is somewhat unique inthat there is little clarity concerning what a model needs to beable to do in order to provide an account of how the mean-ings of complex linguistic expressions, such as sentences, areunderstood. To help address this problem, we introduce a tree-structured neural model that is trained to generate further sen-tences that follow from an input sentence. These further sen-tences chart out the “inferential role” of the input sentence,which we argue constitutes an important part of its meaning.The model is trained using the Stanford Natural Language In-ference (SNLI) dataset, and to evaluate its performance, we re-port entailment prediction accuracies on a set of test sentencesnot present in the training data. We also report the results of asimple study that compares human plausibility ratings for bothground-truth and model-generated entailments for a randomselection of sentences in this test set. Finally, we examine anumber of qualitative features of the model’s ability to gener-alize. Taken together, these analyses indicate that our modelis able to accurately account for important inferential relation-ships amongst linguistic expressions.

Past research on action planning has shed light on the neuralmechanisms underlying the selection of simple motor actions,along with the cognitive mechanisms underlying the planningof action sequences in constrained problem solving domains.We extend this research by describing a neural model thatrapidly plans action sequences in relatively unconstrained do-mains by manipulating structured representations of objectsand the actions they typically afford. We provide an analysisthat indicates our model is able to reliably accomplish goalsthat require correctly performing a sequence of up to 5 actionsin a simulated environment. We also provide an analysis ofthe scaling properties of our model with respect to the num-ber of objects and affordances that constitute its knowledgeof the environment. Using simplified simulations we find thatour model is likely to function effectively while picking from10,000 actions related to 25,000 objects.