David Yenicelik


2020

pdf bib
How does BERT capture semantics? A closer look at polysemous words
David Yenicelik | Florian Schmidt | Yannic Kilcher
Proceedings of the Third BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP

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.