Papers › How does BERT capture semantics? A closer look at polysemous words

How does BERT capture semantics? A closer look at polysemous words

1 Nov 2020EMNLP (BlackboxNLP) 2020 11archive 2025-07-28

David Yenicelik, Florian Schmidt, Yannic Kilcher

The recent paradigm shift to contextual word embeddings has seen tremendous success across a wide range of down-stream tasks. However, little is known on how the emergent relation of context and semantics manifests geometrically. We investigate polysemous words as one particularly prominent instance of semantic organization. Our rigorous quantitative analysis of linear separability and cluster organization in embedding vectors produced by BERT shows that semantics do not surface as isolated clusters but form seamless structures, tightly coupled with sentiment and syntax.

PaperPDFCode

Code

yenicelik/masterthesis officialpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Semantic SimilaritySemanticity predictionWord EmbeddingsWord Sense DisambiguationWord Sense InductionWord Similarity

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections