Large language models (LLMs) have made significant progress in NLP. However, their
ability to memorize, represent, and leverage commonsense knowledge has been a well …

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 …

Recent advances in text-to-image synthesis make it possible to visualize machine
imaginations for a given context. On the other hand, when generating text, human writers are …

The success of language models has inspired the NLP community to attend to tasks that
require implicit and complex reasoning, relying on human-like commonsense mechanisms …

The spread of misinformation, propaganda, and flawed argumentation has been amplified in
the Internet era. Given the volume of data and the subtlety of identifying violations of …

While vertical thinking relies on logical and commonsense reasoning, lateral thinking
requires systems to defy commonsense associations and overwrite them through …

Procedural text understanding is a challenging language reasoning task that requires
models to track entity states across the development of a narrative. A complete procedural …

Intelligent Traffic Monitoring (ITMo) technologies hold the potential for improving road
safety/security and for enabling smart city infrastructure. Understanding traffic situations …

Protein language models, trained on millions of biologically observed sequences, generate
feature-rich numerical representations of protein sequences. These representations, called …

Self-supervision with synthetic training data built from knowledge graphs has been proven
useful to enhance the language model accuracy in zero-shot evaluation on commonsense …