In the last decade, deep artificial neural networks have achieved astounding performance in
many natural language-processing tasks. Given the high productivity of language, these …

State-of-the-art machine learning methods exhibit limited compositional generalization. At
the same time, there is a lack of realistic benchmarks that comprehensively measure this …

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 …

The ability to generalise well is one of the primary desiderata of natural language
processing (NLP). Yet, what'good generalisation'entails and how it should be evaluated is …

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) …

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

Flexible neural sequence models outperform grammar-and automaton-based counterparts
on a variety of tasks. However, neural models perform poorly in settings requiring …

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

Abstract Machine learning has achieved tremendous success in a variety of domains in
recent years. However, a lot of these success stories have been in places where the training …