Paper Details

Published: 2024/08/13

DOI: 10.48550/arXiv.2408.07190

ARXIV ID: 2408.07190v1

In this paper, the authors bring tools from natural language processing into the domain of conceptual engineering, a branch of philosophy dealing with how to change public usage of words and phrases. The authors use the spoken component of the British National Corpus and BERT to create contextualised word embeddings, and use Gaussian Mixture Models, a selection of metrics, and qualitative analysis to visualise and numerically represent lexical landscapes.