Suggestions

• What is the value in the hundred and twenty-eighth row and hundred and twenty-fourth column?

• What are the BLEU scores achieved by the Transformer model on machine translation tasks?

• What is the value in the sixty-fourth row and sixtieth column?

• What are positional encodings?

• What is the value in the hundred and twenty-second row and hundred and eighteenth column?

• What is the complexity of a separable convolution?

• What is the value in the hundred and fifty-third row and hundred and forty-ninth column?

• How were sentence pairs batched together?