SBERT Embeddings from Conversations


I have a dataset consisting of text-based conversations between two humans. One conversation has on average 20 turns and can look as follows:

Person 1: Do you like cooking?
Person 2: Yes. I like cooking very much. I got this hobby when I was 12 years sold.
Person 1: Why do you like it?
Person 2: I have no idea. I like cooking by myself. I like to taste delicious food.

With SBERT I can get the embeddings of one turn (e.g., “Hello there, how are you doing?”). Is it also possible to get one embedding with SBERT for several turns or a whole conversation (20 turns)? Are there other models which are capable to do this or are more recent? Afterward, I would like to project the embedding to 2D or 3D space and apply clustering.

hi, what is your task basically?

I would like to generate embeddings of conversations and then cluster them (the projected embeddings or the original embeddings) to extract certain clusters that correspond for example to different topics of the conversations. So each conversation has a specific topic or style etc. and I assume that his is visible in embeddings.