Untangling homonym representations in BERT, Part 2: Phenomenology
In this post, I’ll use the tools from the previous post to examine BERT-Base, an open source deep transformer model which performs well on natural language processing benchmarks (see the first link). We will find that in deeper layers, this model has learned to represent homonyms in such a way that they can be easily discriminated. This post will cover just the phenomenology: to what extent are the representations of two homonyms disentangled from each other in each layer? In the next post, we will dive into how the representations come to be disentangled from each other.