BERT's Conceptual Cartography: Mapping the Landscapes of Meaning
Nina Haket, Ryan Daniels

TL;DR
This paper introduces a novel method for visualizing and analyzing the contextual nuances of words using BERT embeddings and Gaussian Mixture Models, aiding conceptual engineers in understanding word usage variability.
Contribution
It pioneers the creation of 2D lexical landscapes to represent pragmatic word usage, providing a new tool for conceptual engineering research.
Findings
Each word has a unique, complex landscape.
One-size-fits-all approaches are ineffective for word improvement.
The method reveals the intricate variability in word contexts.
Abstract
Conceptual Engineers want to make words better. However, they often underestimate how varied our usage of words is. In this paper, we take the first steps in exploring the contextual nuances of words by creating conceptual landscapes -- 2D surfaces representing the pragmatic usage of words -- that conceptual engineers can use to inform their projects. We 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. Such an approach has not yet been used in the conceptual engineering literature and provides a detailed examination of how different words manifest in various contexts that is potentially useful to conceptual engineering projects. Our findings highlight the inherent complexity of conceptual…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsLanguage, Metaphor, and Cognition · Natural Language Processing Techniques · Language and cultural evolution
MethodsRefunds@Expedia|||How do I get a full refund from Expedia? · Attention Is All You Need · Linear Layer · Attention Dropout · Dense Connections · Dropout · Residual Connection · WordPiece · Layer Normalization · Multi-Head Attention
