Ask Wikipedia ELI5-like Questions Using Long-Form Question Answering on Haystack

Recent advancements in NLP question answering (QA)-based systems have been astonishing. QA systems built on top of the most recent language models (BERT, RoBERTa, etc.) can answer factoid-based questions with relative ease and excellent precision. The task involves finding the relevant document passages containing the answer and extracting the answer by scanning the correct word token span. More challenging QA systems engage with so-called "generative question answering". These systems focus on handling questions where the provided context passages are not simply the source tokens for extracted answers, but provide the larger context to synthesize original answers.