Question Answering no-context

Beginners
1

Hello everyone,
I have dataset of medicine questions it looks like [{“question”:question, “answer”:answer}, {“question”:question, “answer”:answer}, …]
I neeed to train a model which would give me answer based on my question
It should be something like FAQ

As input I will provide new question and model should give me one of the answers in dataset

I tried to find something similar but only thing I could find was QA with context and Text Classsification Positive or Negative(

Any thoughts?

Thanks

2

Hello,

You can probably consider a RAG approach to do this.
Thanks

3

You can either convert this into csv or a table structure use a TAPAS model from google to get the answer or use LLM to get answer using the technique called RAG