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

Chain-of-thought prompting has demonstrated remarkable performance on various natural
language reasoning tasks. However, it tends to perform poorly on tasks which requires …

The field of meta-learning, or learning-to-learn, has seen a dramatic rise in interest in recent
years. Contrary to conventional approaches to AI where tasks are solved from scratch using …

Humans can reason compositionally when presented with new tasks. Previous research
shows that appropriate prompting techniques enable large language models (LLMs) to …

Natural language is characterized by compositionality: the meaning of a complex expression
is constructed from the meanings of its constituent parts. To facilitate the evaluation of the …

We present a survey covering the state of the art in low-resource machine translation (MT)
research. There are currently around 7,000 languages spoken in the world and almost all …

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 …

Recently, many datasets have been proposed to test the systematic generalization ability of
neural networks. The companion baseline Transformers, typically trained with default hyper …

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 …

Learning representations of algorithms is an emerging area of machine learning, seeking to
bridge concepts from neural networks with classical algorithms. Several important works …