Visualizing embeddings & improving accuracy

[shivomthakkar]

Hey,

First off, thanks for your amazing implementation of Custom NER. I have been using it for my project.

I am facing this issue where sometimes the data gets tagged to the wrong entity name. Now I know that we cannot have 100% accuracy, but I was wondering if there was any changes that I could make in the code that would help me visualize my model, or understand exactly what is going on and how I can maybe improve it?