The power of human language and thought arises from systematic compositionality—the
algebraic ability to understand and produce novel combinations from known components …

A major goal of artificial intelligence (AI) is to create an agent capable of acquiring a general
understanding of the world. Such an agent would require the ability to continually …

The ability to extrapolate, ie, to make predictions on sequences that are longer than those
presented as training examples, is a challenging problem for current deep learning models …

Human intelligence exhibits compositional generalization (ie, the capacity to understand
and produce unseen combinations of seen components), but current neural seq2seq …

Despite the tremendous success, existing machine learning models still fall short of human-
like systematic generalization--learning compositional rules from limited data and applying …

Abstract We propose Beam Tree Recursive Cell (BT-Cell)-a backpropagation-friendly
framework to extend Recursive Neural Networks (RvNNs) with beam search for latent …

Abstract Recursive Neural Networks (RvNNs), which compose sequences according to their
underlying hierarchical syntactic structure, have performed well in several natural language …

Posets are discrete mathematical structures which are ubiquitous in a broad range of data
analysis and machine learning applications. Research connecting posets to the data …

Existing neural models are demonstrated to struggle with compositional generalization (CG),
ie, the ability to systematically generalize to unseen compositions of seen components. A …

Improving the generalization ability of reinforcement learning (RL) agents is an open and
challenging problem and has gradually received attention in recent years. Previous work …