Questions

Let's put our knowledge to the test. Try answering the following questions:

1. How do you use the pre-trained BERT model?
2. What is the use of the [PAD] token?
3. What is an attention mask?
4. What is fine-tuning?
5. How do you compute the starting index of an answer in question-answering?
6. How do you compute the ending index of an answer in question-answering?
7. How do you use BERT for NER?