Probing classifiers have emerged as one of the prominent methodologies for interpreting
and analyzing deep neural network models of natural language processing. The basic idea …

The field of natural language processing has seen impressive progress in recent years, with
neural network models replacing many of the traditional systems. A plethora of new models …

AI is undergoing a paradigm shift with the rise of models (eg, BERT, DALL-E, GPT-3) that are
trained on broad data at scale and are adaptable to a wide range of downstream tasks. We …

Transformer architectures have proven to learn useful representations for protein
classification and generation tasks. However, these representations present challenges in …

Despite a multitude of empirical studies, little consensus exists on whether neural networks
are able to generalise compositionally, a controversy that, in part, stems from a lack of …

We investigate how neural networks can learn and process languages with hierarchical,
compositional semantics. To this end, we define the artifical task of processing nested …

End-to-end neural Natural Language Processing (NLP) models are notoriously difficult to
understand. This has given rise to numerous efforts towards model explainability in recent …

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 …

Deep learning has recently come to dominate computational linguistics, leading to claims of
human-level performance in a range of language processing tasks. Like much previous …

Several studies have reported the inability of Transformer models to generalize
compositionally, a key type of generalization in many NLP tasks such as semantic parsing …