Back to questions

Adding meaningful embeddings to the two-tower model

There is a DSSM-like model trained in click-through sessions with the original, positive and negative merchandise. How to add text embedding products from LLM?

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
Adding meaningful embeddings to the two-tower model — interview question — ML Mentor