What is the difference between training(https://www.sbert.net/docs/training/overview.html#training-data) and unsupervised learning

[SAIVENKATARAJU]

Hi,

I have some bunch of PDF's and I am building a QnA system from the pdf's. Currently, I am using deepset/haystack repo for the same task.

My doubt is if we want to generate embeddings for my text which training I should do, what is the difference as both approaches mostly takes sentences right?

[nreimers]

Unsupervised training does not yet work well. Unsupervised learning is still in an active research phase and the performances are not yet as good as the performances of the pre-trained models.

There are several pre-trained models, that work quite well for most use cases. If you need better performances, I recommend to create training data and to do supervised training on it.

[SAIVENKATARAJU]

But when i checking the documentation, w.r.t data making is same for the both the approaches. especially for the semantic similarity. just confused what makes difference between these two approaches

[nreimers]

For the one you have some labeled or structured data, which you exploit, like (question, answer) pairs.

For unsupervised approaches, you just have text without any labels or structure.