Scalar inferences (SI) are a signature example of how humans interpret language based on
unspoken alternatives. While empirical studies have demonstrated that human SI rates are …

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

Language models contain ranking-based knowledge and are powerful solvers of in-context
ranking tasks. For instance, they may have parametric knowledge about the ordering of …

Previous work has demonstrated that pre-trained large language models (LLM) acquire
knowledge during pre-training which enables reasoning over relationships between words …

Scalar inferences occur when a weaker statement like It's warm is used when a stronger one
like It's hot could have been used instead, resulting in the inference that whoever produced …

We present a method for exploring regions around individual points in a contextualized
vector space (particularly, BERT space), as a way to investigate how these regions …

Existing pre-trained transformer analysis works usually focus only on one or two model
families at a time, overlooking the variability of the architecture and pre-training objectives. In …

It is an open question what semantic representations transformer-based language models
can encode and whether they have access to more abstract aspects of semantic meaning …

Vector space models of word meaning all share the assumption that words occurring in
similar contexts have similar meanings. In such models, words that are similar in their topical …

The representation space of pretrained Language Models (LMs) encodes rich information
about words and their relationships (eg, similarity, hypernymy, polysemy) as well as abstract …