How you calculate similarity after having the embedding?

by vega6000 - opened Dec 11, 2023

Discussion

vega6000

Dec 11, 2023

•

edited Dec 11, 2023

Hi, sorry I am new to this, after your have the phrase embedding do you use:

similatiry = cosine_similarity([sentence_embedding1], [sentence_embedding2])

it supposely gives a value between -1 and 1 what value do you agree beeing similar meaning? >0.5?

thank you for the suppport!

tomaarsen

Sentence Transformers org Dec 11, 2023

Cosine similarity indeed, although the output range is between 0 and 1. You can use the cos_sim function if you'd like.
Perhaps >0.7 or >0.8 is quite similar - this is a bit subjective.

I'll close this for now, but feel free to respond if you have questions.

tomaarsen changed discussion status to closed Dec 11, 2023

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment