Both open domain and closed domain Q&A looks promising to use as a framework. Could also extract an answer from wikipedia which is then used an additional input to generate the answer.
Idea: I can give context as a long articles (e.g. wikipedia), and then apply the logic above. This allows us to give long context, while still being about a fairly specific topic (e.g. Donald trump's wikipedia).
Both open domain and closed domain Q&A looks promising to use as a framework. Could also extract an answer from wikipedia which is then used an additional input to generate the answer.
Idea: I can give context as a long articles (e.g. wikipedia), and then apply the logic above. This allows us to give long context, while still being about a fairly specific topic (e.g. Donald trump's wikipedia).
https://docs.google.com/presentation/d/1A5wJEzFYGdNem7egJ-BTm6EMI3jGNe1lalyChYL54gw/edit#slide=id.g72fe29dbfb_0_96
Weaver paper: https://arxiv.org/pdf/1804.10490.pdf