Hey there, everyone. Can anyone please let me know how I might be able to generate FAQ type questions using few shot learning?
It might be a bit confusing without some examples, so here are some.
For example, given a text/passage:
“Natural language processing (NLP) refers to the branch of computer science—and more specifically, the branch of artificial intelligence or AI—concerned with giving computers the ability to understand text and spoken words in much the same way human beings can”
- Which branch of AI is concerned with giving computers the ability to understand text and spoken words? Ans: NLP
- NLP is a branch of what? Ans: Computer Science
- To whom is NLP concerned with giving the ability to understand text and spoken words? Ans: Computers
- NLP is concerned with giving computers the ability to understand what? Ans: Text and spoken words
and so on. Answers for all of these questions would be either a single word or a single term
Can anyone please direct me to any research paper or tutorials/models that achieves the above objective? Few-shot learning is critical because I currently lack the resources to fine-tune a LLM. Is it even possible with FSL? If not I would love to know the alternative approaches.