1

Problem I have at hand is to build a product suggestion model which suggest products based on the context of the search query of a user. My plan is to get a pre-trained model from the sentence-transformers pre-trained models and embed product descriptions using that and then get a list of top k most semantically similar products to the encoded query which user typed using the same model. I want to know how should I prepare my dataset to finetune the model to the product domain (e-commerce). Data set I have is called the amazon-esci dataset which has products relevant to search queries by users, labelled.

I tried to directly use the pre-trained model. But it suggest irrelevant products. I would like to know how to fine-tune the model.

L.D. WEERARATHNE
  • 11
  • 1
  • Welcome to Stackoverflow! Asking for recommendations might not be appropriate on the Stackoverflow (https://stackoverflow.com/help/how-to-ask) but it might be possible to ask the question on https://softwarerecs.stackexchange.com. Also, logging it on https://stackoverflow.com/collectives/nlp/beta/discussions/76949597 – alvas Aug 25 '23 at 16:30
  • 2
    @alvas The question here appears to be "I would like to know how to fine-tune the model.", which is not a recommendation request. – Ryan M Aug 25 '23 at 22:26

0 Answers0