search

huggingface / setfit

Efficient few-shot learning with Sentence Transformers
https://hf.co/docs/setfit
Apache License 2.0
2.18k stars 221 forks source link

Compare with other approaches #227

Open creatorrr opened 1 year ago

creatorrr commented 1 year ago

Dumb question:

How does setfit compare with other approaches for sentence classification in low data settings? Two that may be worth comparing to:

Pros and cons of these approaches? Thoughts?

tomaarsen commented 1 year ago

The augmented SBERT link is faulty: there's a / missing. The augmented SBERT link does work.

Those would be very interesting to compare against. I'm not sure if anyone has tried to do so yet.

creatorrr commented 1 year ago

Thanks for the correction. :)

creatorrr commented 1 year ago

Yes I agree. Is there some dataset that we could use as a good benchmark?