Back to questions

BERT pooling, sentence transformers and metric-learning analogy

How can you get a sentence embedding from BERT, how do sentence transformers differ, and why is this similar to metric learning for image pairs?

Answer as you would in an interview

Answer aloud or write down a few key points. The text field is optional; the review opens after your attempt.

Loading
BERT pooling, sentence transformers and metric-learning analogy — interview question — ML Mentor