Cosine similarity of contextual embeddings is used in many NLP tasks (eg, QA, IR, MT) and
metrics (eg, BERTScore). Here, we uncover systematic ways in which word similarities …

We conduct a pilot study selectively evaluating the cognitive abilities (decision making and
spatial reasoning) of two recently released generative transformer models, ChatGPT and …

We present a detailed case study evaluating selective cognitive abilities (decision making
and spatial reasoning) of two recently released generative transformer models, ChatGPT …

The paper studies domain-transfer capabilities of the machine reading comprehension
model (MRC) in named entity recognition task. In such a task, the model is required to …

The current study quantitatively (and qualitatively for an illustrative purpose) analyzes
BERT's layer-wise masked word prediction on an English corpus, and finds that (1) the …

The focus of this thesis is broadly on the alignment of lexicographical data, particularly
dictionaries. In order to tackle some of the challenges in this field, two main tasks of word …

We present Xposition, an online platform for documenting adpositional semantics across
languages in terms of supersenses (Schneider et al., 2018). More than just a lexical …

The purpose of this study was to evaluate the effectiveness of using natural language
processing (NLP) artificial intelligence (AI) in enterprise resources planning (ERP) to identify …

Contextualized word embedding (CWE) models such as BERT (Devlin et al.(2019)) have
been used in many NLP tasks. Gessler and Schneider (2021)(G&S) focus on the use of …

To a first approximation, understanding the meaning of a sentence involves understanding
the meanings of individual words, and how they relate to one another as signaled by …