The success of large pretrained language models (LMs) such as BERT and RoBERTa has
sparked interest in probing their representations, in order to unveil what types of knowledge …

The design of widespread vision-and-language datasets and pre-trained encoders directly
adopts, or draws inspiration from, the concepts and images of ImageNet. While one can …

Unfair stereotypical biases (eg, gender, racial, or religious biases) encoded in modern
pretrained language models (PLMs) have negative ethical implications for widespread …

In order to simulate human language capacity, natural language processing systems must
be able to reason about the dynamics of everyday situations, including their possible causes …

An increasing awareness of biased patterns in natural language processing resources such
as BERT has motivated many metrics to quantify 'bias' and 'fairness' in these resources …

Pretrained Masked Language Models (MLMs) have revolutionised NLP in recent years.
However, previous work has indicated that off-the-shelf MLMs are not effective as universal …

The societal impact of pre-trained language models has prompted researchers to probe
them for strong associations between protected attributes and value-loaded terms, from slur …

Recent advancements in high-quality, large-scale English resources have pushed the
frontier of English Automatic Text Simplification (ATS) research. However, less work has …

Humans acquire their native languages by taking part in communicative interactions with
their caregivers. These interactions are meaningful, intentional, and situated in their …

Vector-based word representation paradigms situate lexical meaning at different levels of
abstraction. Distributional and static embedding models generate a single vector per word …