Is there a Hugging Face Transformer that takes 2 contexts as input for question answering? For example, I could have transcript of a meeting in first context and agenda of the meeting in the second context. Then ask a question - Did the meeting adhere to the discussion topics given in the agenda? Alternatively, can you suggest how to solve such types of question answering problems that might require multiple contexts?

  • $\begingroup$ You could always just try and combine the two contexts right? $\endgroup$ Dec 18, 2022 at 12:05
  • $\begingroup$ yeach I could do that too. But a transformer with 2 separate contexts is a lot cleaner IMHO. $\endgroup$
    – John Watts
    Dec 21, 2022 at 6:40


You must log in to answer this question.