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

Rapid progress in machine learning for natural language processing has the potential to
transform debates about how humans learn language. However, the learning environments …

Research seeking to build artificial systems capable of reproducing elements of human
intelligence may benefit from a deeper consideration of the architecture and learning …

Sequence-to-sequence models excel at handling natural language variation, but have been
shown to struggle with out-of-distribution compositional generalization. This has motivated …

We propose a simple data augmentation protocol aimed at providing a compositional
inductive bias in conditional and unconditional sequence models. Under this protocol …

People can learn a new concept and use it compositionally, understanding how to" blicket
twice" after learning how to" blicket." In contrast, powerful sequence-to-sequence (seq2seq) …

The field of compositional generalization is currently experiencing a renaissance in AI, as
novel problem settings and algorithms motivated by various practical applications are being …

Humans easily interpret expressions that describe unfamiliar situations composed from
familiar parts (" greet the pink brontosaurus by the ferris wheel"). Modern neural networks, by …

Large language models (LLMs) exhibit dynamic capabilities and appear to comprehend
complex and ambiguous natural language prompts. However, calibrating LLM interactions is …

Obtaining human-like performance in NLP is often argued to require compositional
generalisation. Whether neural networks exhibit this ability is usually studied by training …