Semantic Similarity Measurement in Clinical Text

Transformer-based language models are powerful tools for a variety of natural language processing tasks such as text similarity, question answering, translation, etc.
What are the limitations of these models in specific domains such as biomedicine? How do various domain-specific language models compare to one another? Do models trained on biomedical data perform well on clinical data?
I have delved into these questions in a blog post I wrote on The Ezra Tech Blog.