General Purpose Readers

This video explains some ideas around General Purpose Reader models. The idea is to split up the tasks Deep Learning has gone after into “retrieve“ and then “read“ components. The retriever component offers a lot of flexibility and I am more convinced the read component will have the general adaptability promised by things like the GPT-3 API. Please share any thoughts you have on these ideas! Please subscribe to SeMI Technologies on YouTube for the full podcast with Malte Pietsch discussing several ideas like this: Haystack Pipelines: SQuAD: (single model) (Microsoft Research Asia)&version=v2.0 OpenAI API: Decision Transformer: CO-Search: Chapters 0:00 Introduction 2:36 SQuAD motivating example of retrieva