The ability to cooperate through language is a defining feature of humans. As the
perceptual, motory and planning capabilities of deep artificial networks increase …

The extent to which the linguistic system—its architecture, the representations it operates on,
the constraints it is subject to—is specific to language has broad implications for cognitive …

The ability of algorithms to evolve or learn (compositional) communication protocols has
traditionally been studied in the language evolution literature through the use of emergent …

Deep learning models struggle with compositional generalization, ie the ability to recognize
or generate novel combinations of observed elementary concepts. In hopes of enabling …

Natural language allows us to refer to novel composite concepts by combining expressions
denoting their parts according to systematic rules, a property known as\emph …

Emergent communication aims for a better understanding of human language evolution and
building more efficient representations. We posit that reaching these goals will require …

Many machine learning algorithms represent input data with vector embeddings or discrete
codes. When inputs exhibit compositional structure (eg objects built from parts or procedures …

Compositional generalization, the ability of an agent to generalize to unseen combinations
of latent factors, is easy for humans but hard for deep neural networks. A line of research in …

In tasks like semantic parsing, instruction following, and question answering, standard deep
networks fail to generalize compositionally from small datasets. Many existing approaches …

A fundamental characteristic common to both human vision and natural language is their
compositional nature. Yet despite the performance gains contributed by large vision and …