What Happens To BERT Embeddings During Fine-tuning?

Understand

While there has been much recent work studying how linguistic information is encoded in pre-trained sentence representations, comparatively little is understood about how these models change when adapted to solve downstream tasks.

• Using a suite of analysis techniques (probing classifiers, Representational Similarity Analysis, and model ablations), we investigate how fine-tuning affects the representations of the BERT model.
• We find that while fine-tuning necessarily makes significant changes, it does not lead to catastrophic forgetting of linguistic phenomena.
• We instead find that fine-tuning primarily affects the top layers of BERT, but with noteworthy variation across tasks.